{
  "schema_version": "1.2",
  "release_version": "v2026.10.21",
  "release_date": "2026-10-21",
  "datasets": {
    "calcofi_2022-edna": {
      "provider": "calcofi",
      "dataset": "2022-edna",
      "dataset_name": "CalCOFI October 2022 Vertebrate eDNA",
      "dataset_name_short": "2022 Vertebrate eDNA",
      "category": "Genomics & eDNA",
      "color": "#2e8b57",
      "description": "eDNA metabarcoding survey of vertebrates from water samples collected during the October 2022 CalCOFI cruise. Water filters from CalCOFI/GEMCAP stations off Southern California were run through one or two molecular assays: a mitochondrial D-loop assay (cetacean detections, incl. Delphinus and Megaptera novaeangliae) and a 12S rRNA \"MiFish\" assay (fish detections). Published as an intercalibration exercise (source datasetID \"CalCOFI_Intercal\") on GBIF/OBIS, linked to Patin et al. 2026 (Methods in Ecology and Evolution, https://doi.org/10.1111/2041-210x.70370). Sequence read counts are a semi-quantitative signal of PCR-amplified DNA, not abundance, and are not comparable between assays. Published as detections only: edna_presence = 1 and the read counts. The source archive holds positive detections only, so the absence of a row for a filter and taxon is not a non-detection for this dataset (a filter or assay run with no detection is simply missing, and absence cannot be inferred); this differs from sio_cetacean-edna, where 0 means not detected in a sequenced sample.\n",
      "citation_main": "Patin N, ODonnell G (2026). CalCOFI October 2022 Vertebrate eDNA. Version 1.3. Occurrence dataset. https://doi.org/10.15468/n52j6r\n",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://www.gbif.org/dataset/10524092-539d-4ea4-8539-2e91ad8581a9",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "CC-BY-4.0",
      "pi_names": "Nastassia Patin",
      "doi": "10.15468/n52j6r",
      "license_url": null,
      "acknowledgement": "This work was made possible by the Office of Naval Research Multidisciplinary University Research Initiative (MURI) funding for MMARINeDNA (award no.: N00014-22-1-2719) with additional support from the National Science Foundation (award no.: OCE-2224726). It includes data generated at the UC San Diego IGM Genomics Center utilizing an Illumina NovaSeq 6000 that was purchased with funding from a National Institutes of Health SIG grant (no.: S10 OD026929). We thank the captain and crew of the NOAA Ship Reuben Lasker, Rachel Pound from CalCOFI and Harrison Huang and Dylan Inskeep from the California Department of Fish and Wildlife for their assistance with sample collection.\n",
      "contact": "mailto:nvpatin@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "sample_measurement",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html",
      "coverage_temporal_observed": "2022-10 to 2022-10",
      "coverage_spatial_observed": "33.8–36.3°N, 122.8–119.4°W",
      "coverage_bbox": {
        "lat_min": 33.8101,
        "lat_max": 36.3464,
        "lon_min": -122.8364,
        "lon_max": -119.4034
      }
    },
    "calcofi_bottle-derived": {
      "provider": "calcofi",
      "dataset": "bottle-derived",
      "dataset_name": "CalCOFI Bottle Derived Hydrographic Products",
      "dataset_name_short": "Bottle Derived Products",
      "category": "Physical Oceanography",
      "color": "#3d5aa8",
      "description": "Hydrographic values DERIVED from the CalCOFI Bottle Database rather than measured: spice (spiciness at 0 dbar) and the TEOS-10 sigma-theta at every bottle with a temperature and a salinity, from the start of the record in 1949, computed from each bottle's own temperature and salinity after the provider's quality flags are applied. The bottle database's own sigma-theta, computed by the legacy DECODR software, stays in the CalCOFI Bottle Database beside it.\n",
      "citation_main": "CalCOFI. (2026). CalCOFI Bottle Derived Hydrographic Products (from the CalCOFI Bottle Database 194903-202105). CalCOFI.io. https://calcofi.io/workflows/ingest_calcofi_bottle-derived.html",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/bottle-database/",
      "link_data_source": "https://calcofi.org/data/oceanographic-data/bottle-database/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "obs",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_bottle-derived.html",
      "coverage_temporal_observed": "1949-02 to 2021-02",
      "coverage_spatial_observed": "18.4–47.9°N, 164.1–106.0°W",
      "coverage_bbox": {
        "lat_min": 18.4167,
        "lat_max": 47.9167,
        "lon_min": -164.0833,
        "lon_max": -105.9667
      }
    },
    "calcofi_bottle": {
      "provider": "calcofi",
      "dataset": "bottle",
      "dataset_name": "CalCOFI Bottle Database",
      "dataset_name_short": "Hydrographic Bottle",
      "category": "Physical Oceanography",
      "color": "#718fdd",
      "description": "Hydrographic bottle data including temperature, salinity, oxygen, nutrients, pigments, and C14 from CalCOFI cruises. The provider publishes it as two linked files: Cast, one row per hydrographic cast (the rosette the bottles came up on: date, position, weather, bottom depth), and Bottle, one row per bottle depth. That cast is not the CTD Cast Files dataset (calcofi_ctd-cast), although both come from the same station visit.\n",
      "citation_main": "CalCOFI. (2023). CalCOFI Bottle Database 194903-202105. CalCOFI.org.",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/bottle-database/",
      "link_data_source": "https://calcofi.org/downloads/database/CalCOFI_Database_194903-202105_csv_16October2023.zip",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "sample",
        "obs",
        "sample_measurement",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_bottle.html",
      "coverage_temporal_observed": "1949-02 to 2021-05",
      "coverage_spatial_observed": "18.4–47.9°N, 164.1–106.0°W",
      "coverage_bbox": {
        "lat_min": 18.4167,
        "lat_max": 47.9167,
        "lon_min": -164.0833,
        "lon_max": -105.9667
      }
    },
    "calcofi_ctd-cast": {
      "provider": "calcofi",
      "dataset": "ctd-cast",
      "dataset_name": "CalCOFI CTD Cast Files",
      "dataset_name_short": "CTD Cast Files",
      "category": "Physical Oceanography",
      "color": "#10a74a",
      "description": "CTD downcast profiles with temperature, salinity, oxygen, fluorescence, and other sensors at standard depths. 1 m-binned final data for 1993-2002 come from the SIO-CalCOFI Technical Group's own archive (J. Wilkinson), which covers the decade calcofi.org does not publish finals for; 1998 and 2003 onward come from calcofi.org. Where both publish the same cruise, calcofi.org is used; the two agree on 130 of 140 comparable files, and the four cruises that differ are recorded in question calcofi_ctd-cast_20.\n",
      "citation_main": "CalCOFI. (2023). CalCOFI CTD Cast Files. CalCOFI.org.",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/ctd-cast-files/",
      "link_data_source": "https://calcofi.org/data/oceanographic-data/ctd-cast-files/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": "rswalethorp@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "obs_ctd_full",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html",
      "coverage_temporal_observed": "1993-08 to 2026-07",
      "coverage_spatial_observed": "29.8–37.8°N, 126.5–117.3°W",
      "coverage_bbox": {
        "lat_min": 29.8268,
        "lat_max": 37.8491,
        "lon_min": -126.4843,
        "lon_max": -117.2734
      }
    },
    "calcofi_ctd-derived": {
      "provider": "calcofi",
      "dataset": "ctd-derived",
      "dataset_name": "CalCOFI CTD Derived Hydrographic Products",
      "dataset_name_short": "CTD Derived Products",
      "category": "Physical Oceanography",
      "color": "#0f7a5a",
      "description": "Hydrographic products DERIVED from the CalCOFI CTD cast profiles rather than measured: spice (spiciness at 0 dbar, TEOS-10) and the sensor-pair averaged sigma-theta at every published CTD depth; and, per cast, the mixed-layer depth (the CalCOFI legacy definition, with two alternative criteria beside it), the depth and value of the chlorophyll-a maximum and the chlorophyll-a integrated over the top 200 m, by the definitions of the CalCOFI CTD team. Computed from the full-resolution 1 m bins of the CalCOFI CTD Cast Files after the provider's quality flags are applied.\n",
      "citation_main": "CalCOFI. (2026). CalCOFI CTD Derived Hydrographic Products (from the CalCOFI CTD Cast Files). CalCOFI.io. https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/ctd-cast-files/",
      "link_data_source": "https://calcofi.org/data/oceanographic-data/ctd-cast-files/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "obs",
        "sample_measurement",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html",
      "coverage_temporal_observed": "1993-08 to 2026-07",
      "coverage_spatial_observed": "29.8–37.8°N, 126.5–117.3°W",
      "coverage_bbox": {
        "lat_min": 29.8268,
        "lat_max": 37.8491,
        "lon_min": -126.4843,
        "lon_max": -117.2734
      }
    },
    "calcofi_dic": {
      "provider": "calcofi",
      "dataset": "dic",
      "dataset_name": "CalCOFI DIC",
      "dataset_name_short": "Carbonate Chemistry / DIC",
      "category": "Carbonate System",
      "color": "#cf2407",
      "description": "Discrete profile dissolved inorganic carbon (DIC) and total alkalinity (TA) from CalCOFI Niskin bottle samples, quality-controlled using WOCE flagging. Values on a Niskin the bottle database also carries are published once, on that bottle. Values on a sample that matches no bottle cast are published too, wherever the source gives the sample a depth, on the sample's own key: they are not linked to a bottle cast (the source names none), and the date of most of them is month-precision only (see questions calcofi_dic_01 and calcofi_dic_07).\n",
      "citation_main": "Keeling, C.D.; Lueker, T.J.; Emanuele, G.; Dickson, A.G.; Martz, T.R.; Wolfe, W.H.; Mau, A. (2025). Discrete profile dissolved inorganic carbon, total alkalinity, water temperature and salinity measurements for CalCOFI (NCEI Accession 0301029). NOAA NCEI. https://doi.org/10.25921/3w9f-jd72",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/dic/",
      "link_data_source": "https://www.ncei.noaa.gov/access/metadata/landing-page/bin/iso?id=gov.noaa.nodc:0301029",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "CC-BY-4.0",
      "pi_names": "Todd Martz; Aaron Mau",
      "doi": "10.25921/3w9f-jd72",
      "license_url": null,
      "acknowledgement": null,
      "contact": "ncei.info@noaa.gov",
      "tables": [
        "sample",
        "obs",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_dic.html",
      "coverage_temporal_observed": "1983-03 to 2021-07",
      "coverage_spatial_observed": "28.1–37.0°N, 125.1–117.3°W",
      "coverage_bbox": {
        "lat_min": 28.1401,
        "lat_max": 37.0425,
        "lon_min": -125.0533,
        "lon_max": -117.3054
      }
    },
    "calcofi_mets": {
      "provider": "calcofi",
      "dataset": "mets",
      "dataset_name": "CalCOFI METS (Underway TSG/Meteorology)",
      "dataset_name_short": "Underway Meteorological (METS)",
      "category": "Meteorology & Sea State",
      "color": "#5c5dad",
      "description": "Shipboard underway thermosalinograph (TSG) and meteorology data, ~1-minute resolution, recorded continuously along the cruise track.\n",
      "citation_main": "CalCOFI. Underway (METS) TSG/Meteorology Data. CalCOFI.org.",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/oceanographic-data/underway/",
      "link_data_source": "https://calcofi.org/data/oceanographic-data/underway/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": "rswalethorp@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "obs_mets_full",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_mets.html",
      "coverage_temporal_observed": "2004-01 to 2022-11",
      "coverage_spatial_observed": "29.8–37.9°N, 125.8–117.2°W",
      "coverage_bbox": {
        "lat_min": 29.8225,
        "lat_max": 37.8658,
        "lon_min": -125.7906,
        "lon_max": -117.153
      }
    },
    "calcofi_phyllosoma": {
      "provider": "calcofi",
      "dataset": "phyllosoma",
      "dataset_name": "CalCOFI Lobster Phyllosoma",
      "dataset_name_short": "Phyllosoma (Lobster Larvae)",
      "category": "Zooplankton",
      "color": "#8c4f8e",
      "description": "Spiny lobster (Panulirus interruptus) phyllosoma larvae counts by developmental stage from CalCOFI net tows, 1951-2008. Source: EDI knb-lter-cce.188.4 (Koslow).\n",
      "citation_main": "CalCOFI - Scripps Institution of Oceanography and T. Koslow. 2017. Data pertaining to lobster phyllosoma, Panulirus interruptus, collection methods, locations, identification and staging (1951-2008, months of July and August) ver 4. Environmental Data Initiative. https://doi.org/10.6073/pasta/9e38121ebb26f1b59b7b39b2eff844fa",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://portal.edirepository.org/nis/mapbrowse?packageid=knb-lter-cce.188.4",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "J. Anthony Koslow",
      "doi": "10.6073/pasta/9e38121ebb26f1b59b7b39b2eff844fa",
      "license_url": "https://portal.edirepository.org/nis/metadataviewer?packageid=knb-lter-cce.188.4",
      "acknowledgement": null,
      "contact": "tkoslow@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "obs_attribute",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html",
      "coverage_temporal_observed": "1951-07 to 2009-07",
      "coverage_spatial_observed": "31.8–35.1°N, 121.5–117.3°W",
      "coverage_bbox": {
        "lat_min": 31.8464,
        "lat_max": 35.1216,
        "lon_min": -121.5483,
        "lon_max": -117.2736
      }
    },
    "calcofi_phytoplankton": {
      "provider": "calcofi",
      "dataset": "phytoplankton",
      "dataset_name": "CalCOFI Phytoplankton (Venrick)",
      "dataset_name_short": "Phytoplankton",
      "category": "Phytoplankton",
      "color": "#0b7454",
      "description": "Abundance and species composition of phytoplankton (385 taxonomic categories) in the California Current, 1996-2022, by inverted-microscope counts (E. Venrick). Samples from the near-surface \"second depth\" are pooled across stations into four regions (NE, SE, Alley, Offshore; Hayward & Venrick 1998) before counting, so the grain is cruise x region, not per-station. Source: EDI knb-lter-cce.254.4.\n",
      "citation_main": "CalCOFI - Scripps Institution of Oceanography, California Current Ecosystem LTER, and E. Venrick. 2023. Temporal and spatial changes of the abundance and species composition of phytoplankton in the California Current from samples collected aboard CalCOFI cruises from summer 1996 through 2022. ver 4. Environmental Data Initiative. https://doi.org/10.6073/pasta/60edabfbfd85c623fce05822befaa071",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/marine-ecosystem-data/phytoplankton-bacterioplankton/",
      "link_data_source": "https://portal.edirepository.org/nis/mapbrowse?packageid=knb-lter-cce.254.4",
      "coverage_temporal": "1996 to 2022",
      "coverage_spatial": null,
      "license": "CC0-1.0",
      "pi_names": "Elizabeth L. Venrick",
      "doi": "10.6073/pasta/60edabfbfd85c623fce05822befaa071",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "acknowledgement": null,
      "contact": "evenrick@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "taxon_group",
        "region",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html",
      "coverage_spatial_observed": "32.4–33.6°N, 121.7–118.8°W",
      "coverage_bbox": {
        "lat_min": 32.4352,
        "lat_max": 33.5668,
        "lon_min": -121.6543,
        "lon_max": -118.7603
      }
    },
    "cce-lter_euphausiids": {
      "provider": "cce-lter",
      "dataset": "euphausiids",
      "dataset_name": "CCE-LTER Euphausiid Abundance",
      "dataset_name_short": "Euphausiids (Krill)",
      "category": "Euphausiids (Krill)",
      "color": "#9876fa",
      "description": "Species- and life-stage-resolved euphausiid (krill) abundance from CalCOFI / CCE-LTER net tows (BTEDB export), 1951-present, one row per tow x species x life stage. Supersedes the prior single-Abundance- column ingest, which had no taxonomic scope (Q02, now resolved) — units remain provisional pending provider confirmation (Q01).\n",
      "citation_main": "Ohman, M.D. 2022. California Current Ecosystem Euphausiid data, Brinton and Townsend Euphausiid Database (BTEDB) ver 1. Environmental Data Initiative. https://doi.org/10.6073/pasta/4a92a0044bcd1523a4f994ece874a57d",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://portal.edirepository.org/nis/mapbrowse?scope=knb-lter-cce&identifier=313",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "Mark D. Ohman",
      "doi": "10.6073/pasta/4a92a0044bcd1523a4f994ece874a57d",
      "license_url": "https://portal.edirepository.org/nis/metadataviewer?packageid=knb-lter-cce.313.1",
      "acknowledgement": "Data originate from the Brinton and Townsend Euphausiid Database of the Pelagic Invertebrate Collection, Scripps Institution of Oceanography. Supported in recent years by NSF grants to M.D. Ohman and the CCE-LTER site.",
      "contact": "mohman@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html",
      "coverage_temporal_observed": "1951-01 to 2019-04",
      "coverage_spatial_observed": "28.0–46.6°N, 133.5–117.3°W",
      "coverage_bbox": {
        "lat_min": 28,
        "lat_max": 46.6,
        "lon_min": -133.467,
        "lon_max": -117.283
      }
    },
    "cce-lter_iron": {
      "provider": "cce-lter",
      "dataset": "iron",
      "dataset_name": "CCE-LTER Dissolved Iron (CalCOFI Cruises)",
      "dataset_name_short": "Dissolved iron",
      "category": "Nutrients & Chemistry",
      "color": "#b8860b",
      "description": "Dissolved iron (Fe) concentrations from CalCOFI cruises in the southern California Current System, Nov. 2002 - July 2004 (completed). Surface (0 m) samples collected with a pole sampler, analyzed by FeLume flow-injection analysis. The source also carries total iron (no real values) and a shipboard iron-addition bioassay response (Chla response to Fe+, units unconfirmed); neither is released yet.\n",
      "citation_main": "California Current Ecosystem LTER, CalCOFI - Scripps Institution of Oceanography, and K. Barbeau. 2017. Measurements of dissolved inorganic concentrations of nutrient iron and of iron limitation at selected stations and depths from CalCOFI cruises in the California Current System, Nov. 2002 - July 2004 (completed) ver 3. Environmental Data Initiative. https://doi.org/10.6073/pasta/63c4e57f87861db3acaf80d1dec103e1.\n",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://portal.edirepository.org/nis/mapbrowse?packageid=knb-lter-cce.21.3",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "Katherine Barbeau",
      "doi": "10.6073/pasta/63c4e57f87861db3acaf80d1dec103e1",
      "license_url": "https://portal.edirepository.org/nis/mapbrowse?packageid=knb-lter-cce.21.3",
      "acknowledgement": null,
      "contact": "kbarbeau@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cce-lter_iron.html",
      "coverage_temporal_observed": "2002-11 to 2004-07",
      "coverage_spatial_observed": "29.9–35.1°N, 124.3–117.3°W",
      "coverage_bbox": {
        "lat_min": 29.85,
        "lat_max": 35.088,
        "lon_min": -124.323,
        "lon_max": -117.307
      }
    },
    "cce-lter_picoplankton-bacteria": {
      "provider": "cce-lter",
      "dataset": "picoplankton-bacteria",
      "dataset_name": "Picoplankton and Bacteria Abundance (CalCOFI Cruise)",
      "dataset_name_short": "Picoplankton & Bacteria",
      "category": "Picoplankton & Bacteria",
      "color": "#1f88cc",
      "description": "Picophytoplankton (Prochlorococcus, Synechococcus, picoeukaryotes) and heterotrophic bacteria abundances analyzed by flow cytometry (FCM) from CCE-CalCOFI Augmented cruises in the California Current System, 2004-2023 (ongoing). Seawater collected from Niskin bottles at 3-8 depths per station; cells fixed shipboard with paraformaldehyde, stained with a DNA-specific dye, and enumerated on an Altra flow cytometer with dual argon-ion lasers.\n",
      "citation_main": "Landry, M. (2004-2023). Picoplankton and Bacteria Abundance (CalCOFI Cruise). CCE LTER.",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://oceaninformatics.ucsd.edu/datazoo/catalogs/ccelter/datasets/159",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": "Michael Landry",
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": "mlandry@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html",
      "coverage_temporal_observed": "2004-11 to 2023-07",
      "coverage_spatial_observed": "29.8–35.6°N, 124.3–117.3°W",
      "coverage_bbox": {
        "lat_min": 29.83,
        "lat_max": 35.6379,
        "lon_min": -124.33,
        "lon_max": -117.295
      }
    },
    "cce-lter_zoodb": {
      "provider": "cce-lter",
      "dataset": "zoodb",
      "dataset_name": "ZooDB Holoplankton Community",
      "dataset_name_short": "ZooDB (Holoplankton Community)",
      "category": "Zooplankton",
      "color": "#17a490",
      "description": "Holoplankton abundance and carbon biomass by 33 higher taxa (copepods to family, plus amphipods, chaetognaths, salps, pyrosomes, pteropods, ostracods, foraminifera, radiolaria and more) from CalCOFI net tows, 1951-2021, enumerated by microscopy (Ohman Lab / SIO Pelagic Invertebrate Collection). One row per (sample, taxon, measurement_type); unpooled tows are station-resolved, pooled samples are per-cruise regional composites. Raw (uncorrected) abundance per 1000 m3 and per m2, plus biomass mg C/m2.\n",
      "citation_main": null,
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/marine-ecosystem-data/zooplankton/",
      "link_data_source": "https://oceaninformatics.ucsd.edu/zoodb/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "Mark D. Ohman; Bertha Lavaniegos; Linsey Sala",
      "doi": null,
      "license_url": "https://oceaninformatics.ucsd.edu/zoodb/",
      "acknowledgement": "Plankton sample analysis supported by NSF grants to M.D. Ohman and the CCE-LTER site, and by the SIO Pelagic Invertebrate Collection.",
      "contact": "mohman@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html",
      "coverage_temporal_observed": "1951-03 to 2015-04",
      "coverage_spatial_observed": "30.8–37.6°N, 125.8–117.3°W",
      "coverage_bbox": {
        "lat_min": 30.75,
        "lat_max": 37.62,
        "lon_min": -125.78,
        "lon_max": -117.3
      }
    },
    "cce-lter_zooscan": {
      "provider": "cce-lter",
      "dataset": "zooscan",
      "dataset_name": "ZooScan PRPOOS Zooplankton",
      "dataset_name_short": "ZooScan (Imaged Zooplankton)",
      "category": "Zooplankton",
      "color": "#885e08",
      "description": "Zooplankton abundance, carbon biomass, and size (Feret diameter, individual carbon content) from ZooScan optical imaging of CalCOFI / CCE-LTER PRPOOS net tows on lines 80, 87 and 90, 2005-present, machine-classified into 23 bioclasses (copepod groups, euphausiids, chaetognaths, appendicularians, salps, doliolids, pteropods, rhizaria and more). One row per (sample, taxon, measurement_type); per-station tows. Source: SIO Ocean Informatics ZooScan portal (Ohman Lab; interface by Marina Frants).\n",
      "citation_main": null,
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/marine-ecosystem-data/zooplankton/",
      "link_data_source": "https://oceaninformatics.ucsd.edu/zooscandb/",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "Mark D. Ohman; Marina Frants",
      "doi": null,
      "license_url": "https://oceaninformatics.ucsd.edu/zooscandb/",
      "acknowledgement": "Plankton sample analysis supported by NSF grants to M.D. Ohman and the CCE-LTER site.",
      "contact": "mohman@ucsd.edu",
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html",
      "coverage_temporal_observed": "2005-07 to 2026-04",
      "coverage_spatial_observed": "30.4–34.5°N, 124.0–117.8°W",
      "coverage_bbox": {
        "lat_min": 30.42,
        "lat_max": 34.45,
        "lon_min": -124,
        "lon_max": -117.77
      }
    },
    "cdfw_dungeness-crab": {
      "provider": "cdfw",
      "dataset": "dungeness-crab",
      "dataset_name": "CDFW Dungeness Crab Megalopae",
      "dataset_name_short": "Dungeness Crab Megalopae",
      "category": "Zooplankton",
      "color": "#f028c9",
      "description": "Dungeness crab (Metacarcinus magister) megalopae and larval decapods picked from archived CalCOFI oblique-tow plankton samples, examined for the California Department of Fish and Wildlife. Two efforts: a 2008-2014 time series of 310 sorted samples (A. Klemmedson, 2015) yielding 24 M. magister megalopae from 14 samples, and 216 archived samples from the 1949-2009 sorting log that were examined and found free of M. magister (1984-2009, E. Jones, as of 2012-02-15). Only examined samples are published — the log's remaining unsorted rows are a fact of the archive's inventory, not a sample of this dataset. Spring cruises, CalBOBL oblique tows, lines < 80 / stations < 90. Counts are occurrence in the examined aliquot, not standardized density. Sorting was performed at the SIO Pelagic Invertebrate Collection, where the removed megalopae are archived in vials.\n",
      "citation_main": "Rogers-Bennett, L.; Jones, E.; Klemmedson, A. (2026). CDFW Dungeness Crab Megalopae from archived CalCOFI plankton samples (1949-2014). California Department of Fish and Wildlife, published through CalCOFI / Scripps Institution of Oceanography.\n",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://data.cnra.ca.gov/dataset/sorting-effort-in-2012-and-2015-for-dungeness-crab-megalopae-in-calcofi-plankton-samples",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "CC-BY-4.0",
      "pi_names": "Laura Rogers-Bennett",
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "sample",
        "obs",
        "obs_attribute",
        "sample_measurement",
        "taxon",
        "dataset_taxon"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html",
      "coverage_temporal_observed": "1984-05 to 2014-05",
      "coverage_spatial_observed": "33.5–51.0°N, 132.2–120.7°W",
      "coverage_bbox": {
        "lat_min": 33.46,
        "lat_max": 51.05,
        "lon_min": -132.25,
        "lon_max": -120.675
      }
    },
    "farallon_bird-mammal": {
      "provider": "farallon",
      "dataset": "bird-mammal",
      "dataset_name": "CalCOFI Bird & Mammal Census",
      "dataset_name_short": "Seabirds & Marine Mammals",
      "category": "Seabirds & Marine Mammals",
      "color": "#d86d6f",
      "description": "Bird and mammal observations along CalCOFI (and NMFS, CPR) cruise transects, 1987-present. Transect effort, counts, and species live from NOAA ERDDAP (CAC_FI_SBAS_tr / CAC_FI_SBAS_obs / CAC_FI_SBAS_sp); behavior lookups curated via CCE-LTER DataZoo 255 (PI Bill Sydeman). On CalCOFI cruises the Scripps Whale Acoustics Lab runs its own cetacean line-transect survey (sio_cetacean-sightings) with an independent observer team: both datasets are kept, so a cetacean group seen by both teams appears once in each, and summing the two counts the same animals twice.\n",
      "citation_main": null,
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://oceanview.pfeg.noaa.gov/erddap/tabledap/CAC_FI_SBAS_obs.html",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "CC-BY-4.0",
      "pi_names": "Bill Sydeman",
      "doi": null,
      "license_url": "https://oceanview.pfeg.noaa.gov/CalCOFI/app/resources/docs/Data_Sharing_Agreement_FarallonInstitute.pdf",
      "acknowledgement": "This product uses data collected by the Farallon Institute, U.S. National Oceanic and Atmospheric Association's (NOAA) Integrated Ocean Observing System (IOOS) with funding distributed to the Southern California Coastal Ocean Observing System (SCCOOS), and the U.S. National Science Foundation's (NSF) California Current Ecosystem Long Term Ecological Research (CCE LTER) site under Grant No. OCE 2142918 (and earlier awards). Earlier financial and organizational support for these seabird observations was also provided through generous gifts from the National Fish and Wildlife Foundation, Moore Family Foundation, Packard Foundation, and Point Blue Conservation Science. We acknowledge data originators and PIs Richard R. Veit, K. David Hyrenbach, and William J. Sydeman.\n",
      "contact": "wsydeman@faralloninstitute.org",
      "tables": [
        "sample",
        "obs",
        "obs_attribute",
        "taxon",
        "dataset_taxon",
        "taxon_group"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html",
      "coverage_temporal_observed": "1987-05 to 2022-10",
      "coverage_spatial_observed": "29.8–37.8°N, 126.5–117.2°W",
      "coverage_bbox": {
        "lat_min": 29.77,
        "lat_max": 37.84,
        "lon_min": -126.47,
        "lon_max": -117.18
      }
    },
    "sio_mesopelagic-fish": {
      "provider": "sio",
      "dataset": "mesopelagic-fish",
      "dataset_name": "UCSD SIO Mesopelagic Fish",
      "dataset_name_short": "Mesopelagic Fish",
      "category": "Mesopelagic Fish",
      "color": "#a809d1",
      "description": "Species-resolved mesopelagic fish counts (90 named species + 1 unidentified-fish catch-all) from MOHT (Matsuda-Oozeki-Hu Trawl) micronekton net tows, 7 CalCOFI cruises 2010-2012, all on RV New Horizon (NODC 32NM). Larval-fish counts in the same source file are a separate table, not included here.\n",
      "citation_main": "Koslow, J. Anthony (2016). CalCOFI Trawl Data. In California Cooperative Oceanic Fisheries Investigations (CalCOFI): Acoustic and Trawl Data. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0BZ64DH\n",
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://library.ucsd.edu/dc/object/bb9217084g",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "CC-BY-4.0",
      "pi_names": "J. Anthony Koslow",
      "doi": "10.6075/J0BZ64DH",
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html",
      "coverage_temporal_observed": "2010-01 to 2012-02",
      "coverage_spatial_observed": "29.8–35.0°N, 124.3–117.4°W",
      "coverage_bbox": {
        "lat_min": 29.8062,
        "lat_max": 34.956,
        "lon_min": -124.2861,
        "lon_max": -117.3567
      }
    },
    "sio_pic-zooplankton": {
      "provider": "sio",
      "dataset": "pic-zooplankton",
      "dataset_name": "SIO PIC Zooplankton Net Tows",
      "dataset_name_short": "Zooplankton Net Tows",
      "category": "Zooplankton",
      "color": "#1551fd",
      "description": "Zooplankton net-tow sample registry from the SIO Pelagic Invertebrate Collection, scoped to CalCOFI-program expeditions. Position, time, depth, and gear metadata per tow. Includes the historical grid (1950s-80s inshore, Gulf of California and Baja lines), not just the modern pattern. Biovolume measurements are not in the source file and are pending from the provider (see Questions for Data Providers).\n",
      "citation_main": null,
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/marine-ecosystem-data/zooplankton/",
      "link_data_source": "https://scripps.ucsd.edu/pelagic-invertebrate-collection",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": "Rasmus Swalethorp; Ed Weber; Linsey Sala",
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": "sample",
      "workflow_url": "https://calcofi.io/workflows/ingest_sio_pic-zooplankton.html",
      "coverage_temporal_observed": "1939-05 to 2024-04",
      "coverage_spatial_observed": "19.9–51.0°N, 164.1–107.1°W",
      "coverage_bbox": {
        "lat_min": 19.917,
        "lat_max": 51.05,
        "lon_min": -164.083,
        "lon_max": -107.1
      }
    },
    "swfsc_cufes": {
      "provider": "swfsc",
      "dataset": "cufes",
      "dataset_name": "CalCOFI Underway CUFES Fish Eggs",
      "dataset_name_short": "CUFES Fish Eggs",
      "category": "Fish Eggs & Larvae",
      "color": "#af8a11",
      "description": "Continuous Underway Fish Egg Sampler (CUFES) egg counts (sardine, anchovy, jack mackerel, hake, squid, other) and eggs per cubic metre pumped, from CalCOFI cruises since 1996. Sampling is ongoing; the processed record reaches April 2022 and SWFSC's processing lags its staffing (Ed Weber, 2026-10-14). Squid eggs are Abraliopsis felis, the only squid in the region with pelagic eggs. Source: SWFSC's CSV export of its CalCOFI database (Cufes.csv, linked to the cruise list by CruiseId); until release v2026.10.01 the same records were read from NOAA CoastWatch ERDDAP erdCalCOFIcufes.\n",
      "citation_main": null,
      "citation_others": null,
      "link_calcofi_org": null,
      "link_data_source": "https://coastwatch.pfeg.noaa.gov/erddap/tabledap/erdCalCOFIcufes.html",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": "custom",
      "pi_names": "Noelle Bowlin",
      "doi": null,
      "license_url": "https://coastwatch.pfeg.noaa.gov/erddap/tabledap/erdCalCOFIcufes.das",
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "sample",
        "obs",
        "taxon",
        "dataset_taxon",
        "measurement_type"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_swfsc_cufes.html",
      "coverage_temporal_observed": "1996-03 to 2022-04",
      "coverage_spatial_observed": "29.8–54.7°N, 134.1–117.2°W",
      "coverage_bbox": {
        "lat_min": 29.8331,
        "lat_max": 54.7431,
        "lon_min": -134.1163,
        "lon_max": -117.2157
      }
    },
    "swfsc_ichthyo": {
      "provider": "swfsc",
      "dataset": "ichthyo",
      "dataset_name": "SWFSC Ichthyoplankton",
      "dataset_name_short": "Ichthyoplankton",
      "category": "Fish Eggs & Larvae",
      "color": "#d3115d",
      "description": "Ichthyoplankton (fish eggs and larvae) collected by bongo and manta net tows on CalCOFI cruises, processed by SWFSC. Counts are per net, with SWFSC's own effort (volume filtered, standard haul factor, proportion sorted). A tow with no egg, larva or invertebrate record is a true zero: it stays as a sample with its effort, and abundance rows are positive only. Counts of species codes that share a WoRMS AphiaID are summed per net; each code keeps its own name. A tow's and net's maximum depth is SWFSC's NetDepth, the estimated depth of the net when all wire is out (roughly the tow's maximum depth, from wire out and wire angle), not a measured depth: over a shallower sea floor the net did not reach it. Egg stages 12-15 are removed at source. Fish larger than larval size (mostly juveniles), counted in addition to the larvae, are in their own table, fish. Each net's side of a bongo pair and its tow number are in ichthyo_net. MOCNESS tows are not in the source.\n",
      "citation_main": "NOAA Fisheries SWFSC. CalCOFI Ichthyoplankton Database.",
      "citation_others": null,
      "link_calcofi_org": "https://calcofi.org/data/marine-ecosystem-data/fish-eggs-larvae/",
      "link_data_source": "https://www.fisheries.noaa.gov/inport/item/20691",
      "coverage_temporal": null,
      "coverage_spatial": null,
      "license": null,
      "pi_names": null,
      "doi": null,
      "license_url": null,
      "acknowledgement": null,
      "contact": null,
      "tables": [
        "sample",
        "obs",
        "obs_attribute",
        "sample_measurement",
        "taxon",
        "dataset_taxon",
        "cruise",
        "ship",
        "lookup",
        "grid",
        "fish",
        "ichthyo_net"
      ],
      "workflow_url": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html",
      "coverage_temporal_observed": "1951-01 to 2023-01",
      "coverage_spatial_observed": "0.0–54.4°N, 179.8–77.2°W",
      "coverage_bbox": {
        "lat_min": 0.0017,
        "lat_max": 54.385,
        "lon_min": -179.8217,
        "lon_max": -77.2283
      }
    }
  },
  "tables": {
    "sample": {
      "name_long": "Sample",
      "description_md": "One row per physical sampling event at its native grain (site, tow, net, subsample, cast, bottle, water, filter, underway, transect, sighting, deployment, scan, region pool). An adjacency list: `parent_sample_key` points at the containing event and `root_sample_key` at the top of the chain, so counting distinct events at any level is a single `GROUP BY`.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "obs": {
      "name_long": "Observation",
      "description_md": "The occurrence-headline long table: one scalar measurement per row, environmental (`realm = 'env'`) and biological (`realm = 'bio'`) together. Biological taxon is the global `taxon_key`; sub-occurrence detail (length/stage bins, behavior) lives in `obs_attribute`, and event-level effort in `sample_measurement`.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "sample_measurement": {
      "name_long": "Sample Measurement",
      "description_md": "Event-level (effort) measurements: quantities that describe the sampling event itself rather than anything observed in it — net volume filtered, standard haul factor, proportion sorted, bottle cast conditions. Kept apart from `obs` so effort is never mistaken for an observation.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "taxon": {
      "name_long": "Taxon",
      "description_md": "Taxonomic hierarchy for species via WoRMS and ITIS authorities (built from spp.duckdb via recursive CTEs)",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "dataset_taxon": {
      "name_long": "Dataset Taxon",
      "description_md": "Crosswalk from each dataset's own taxon vocabulary to the global `taxon_key`. `obs` resolves its taxon by joining this on (`dataset_key`, `ds_taxa_code`), so a dataset can keep its local codes without leaking them into the shared model.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "measurement_type": {
      "name_long": "Measurement Type",
      "description_md": "",
      "provider": "swfsc",
      "dataset": "cufes",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
    },
    "dataset": {
      "name_long": "Dataset",
      "description_md": "",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "obs_ctd_full": {
      "name_long": "Observation (Full CTD)",
      "description_md": "Supplemental full-resolution CTD scans, identical in shape to `obs`. Excluded from the default table list and the ERD because of its size; opt in with `cc_get_db(supplemental = TRUE)`. The default `obs` carries CTD via the adaptively thinned `ctd_thin`.",
      "provider": "calcofi",
      "dataset": "ctd-cast",
      "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html",
      "supplemental": true
    },
    "obs_mets_full": {
      "name_long": "Obs Mets Full",
      "description_md": "",
      "provider": "calcofi",
      "dataset": "mets",
      "workflow": "https://calcofi.io/workflows/ingest_calcofi_mets.html",
      "supplemental": true
    },
    "obs_attribute": {
      "name_long": "Observation Attribute",
      "description_md": "Sub-occurrence attribution: the breakdown *within* an `obs` headline row. Covers numeric frequency distributions (length bins, stage numbers) and categorical breakdowns (seabird behavior). Counts here sum to the headline where the source is internally consistent.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "taxon_group": {
      "name_long": "Taxon Group",
      "description_md": "Portable groupings of taxa (phytoplankton functional groups, seabirds, marine mammals). Many taxa per group; a taxon may belong to several.",
      "provider": "farallon",
      "dataset": "bird-mammal",
      "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
    },
    "region": {
      "name_long": "Region",
      "description_md": "The 4 pooled regions defined on the CalCOFI grid (Hayward & Venrick 1998), with the member station codes the source declares and a POLYGON derived from them: each declared station claims the water nearest to it, clipped to the convex hull of all 34 stations and dissolved by region, so the four tile their pooled domain with no overlap and no gaps. Stations are placed by the `+proj=calcofi` transform rather than a grid lookup, which is what lets the six intermediate inshore stations with no cell in the regularized grid resolve. latitude/longitude is an interior representative point, not a centroid (the regions are concave). Land is not erased. See questions Q01.",
      "provider": "calcofi",
      "dataset": "phytoplankton",
      "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
    },
    "grid": {
      "name_long": "Grid",
      "description_md": "CalCOFI survey grid polygons with standard and historical station patterns",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "cruise": {
      "name_long": "Cruise",
      "description_md": "unique by ship and year-month",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "ship": {
      "name_long": "Ship",
      "description_md": "unique ship with many cruises",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "lookup": {
      "name_long": "Lookup",
      "description_md": "Unified vocabulary lookup table for egg stages, larva stages, and tow types",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "fish": {
      "name_long": "Fish",
      "description_md": "Fish larger than larval size (SWFSC Fish table): generally juveniles but not exclusively, counted per net and CalCOFI species code in addition to the larvae of the same net, never in both (Ed Weber, 2026-10-14, swfsc_ichthyo_20). Not in obs: no life stage in the vocabulary says exactly \"larger than larval size\".",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "ichthyo_net": {
      "name_long": "Ichthyo Net",
      "description_md": "One row per SWFSC ichthyoplankton net with the two source columns the core projection drops: the net's side of a bongo pair and the tow's number at its station occupation, beside SWFSC's own NetId and TowId and the tow type. Join sample (sample_type = 'net', dataset_key = 'swfsc_ichthyo') USING (sample_key). What tells the two nets of a bongo tow, and two tows of one type at one occupation, apart; the SIO Pelagic Invertebrate Collection's Parent Net Event crosswalk matches on it.",
      "provider": "swfsc",
      "dataset": "ichthyo",
      "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
    },
    "spatial": {
      "name_long": "Spatial Layers",
      "description_md": "Geometries for ancillary spatial layers (CA jurisdictions NOAA boundaries marine protected areas etc.) keyed by spatial_key. Sourced from metadata/spatial_layers.csv. Companion to spatial_attribute.",
      "provider": "calcofi",
      "dataset": "spatial"
    },
    "spatial_attribute": {
      "name_long": "Spatial Layer Attributes",
      "description_md": "Non-geometry attributes for features in spatial in long entity-attribute-value form (spatial_key layer fld and one typed val_* column). Allows attribute schemas to differ across layers without column proliferation.",
      "provider": "calcofi",
      "dataset": "spatial"
    },
    "obs_bio": {
      "name_long": "Biological Observations",
      "description_md": "The bio realm of the observations — one row per taxon occurrence headline (count, density or biomass) with the gear and effort of its own sampling event inline (`tow_type`, `std_haul_factor`, `prop_sorted`, `volume_sampled_m3`), the two standardized densities (`density_per_10m2`, `density_per_1000m3`) and `effort_class`, `qual_ok`, `root_id` (→ `sample_root`), `sample_key` (→ `sample`, the net / tow itself), `hex_id` (H3 res 10) and `hex7`. A strict superset of `obs`'s bio rows under a name mapping (`value` = `measurement_value`, realm implied); `obs` is a view over this table and `obs_env`. One object (~26 MB), read whole by the CalCOFI Explorer. Depth is the observation's, falling back to its sample's span (a net tow) and its root's.",
      "provider": "calcofi",
      "dataset": "calcofi-db-release"
    },
    "obs_env": {
      "name_long": "Environmental Observations",
      "description_md": "The env realm of the observations — one row per measured scalar (bottle, CTD headline series `ctd_thin`, DIC, METS, picoplankton) with the same columns as `obs_bio` (effort and taxon NULL), `qual_ok` evaluated, `root_id` (→ `sample_root`), `sample_key` (→ `sample`, the bottle / cast), `hex_id` and `hex7`. Hive-partitioned by `measurement_type` so one variable is one object (~4 MB median); `obs` is a view over `obs_bio` and this table. A strict superset of `obs`'s env rows under a name mapping (`value` = `measurement_value`).",
      "provider": "calcofi",
      "dataset": "calcofi-db-release"
    },
    "climatology": {
      "name_long": "Climatology",
      "description_md": "The one seasonal baseline every CalCOFI anomaly is a departure from (calcofi4db::build_climatology(), release_database.qmd browser_objects). A plain mean of the env realm of obs per dataset × station (site_key, with grid_key as the station's modal cell) × calendar month × 10 m floor depth bin × measurement type across the window stamped on every row (clim_yr_min–clim_yr_max, 1993–2013), kept only where at least 5 distinct cruises contribute. Calendar month because CalCOFI's quarterly cruises give many years per month at a station but few days; 10 m floor bins (labelled by the shallow edge) because obs carries the thinned CTD series and 5 m off-grid bins sample only the profile's inflection points. Partitioned by measurement_type. ctd-transects, the Explorer's Sections lens and calcofi4r::cc_climatology() subtract this table; a cell that is absent has no baseline and its anomaly is blank, never zero.",
      "provider": "calcofi",
      "dataset": "calcofi-db-release"
    },
    "sample_root": {
      "name_long": "Root Samples",
      "description_md": "One row per root sampling event (a `sample` with no parent) with the dense integer `root_id` the browser objects (`obs_bio`, `obs_env`, `sample_spatial`) join on, its position, datetime, depth span, gear and GEBCO seafloor depth. Supplemental: built by release_database.qmd, hidden from `cc_get_db()` unless `supplemental = TRUE`.",
      "provider": "calcofi",
      "dataset": "release",
      "supplemental": true
    },
    "sample_spatial": {
      "name_long": "Sample Spatial Membership",
      "description_md": "Exact polygon membership per root sample — one row per (root sample, spatial feature) for every layer in `spatial` — computed once at release so every consumer inherits the same membership (Explorer plan D4). Keyed on (`root_sample_key`, `spatial_key`).",
      "provider": "calcofi",
      "dataset": "release"
    },
    "grid_crosswalk": {
      "name_long": "Grid Crosswalk",
      "description_md": "How the cells of the previous CalCOFI grid (every release through v2026.10.01; `calcofi4r::cc_grid_v1`) map onto the cells of this release's `grid`, rebuilt as one cell per official station beside the previous cells kept as they were (CalCOFI/workflows#130). One row per overlapping pair of a previous and a current cell, with the overlap area and its share of each cell (`prev_frac`, `grid_frac`), built at release by calcofi4db::build_grid_crosswalk() and gated by check_grid_crosswalk(). 196 of the 218 previous keys are also keys of the rebuilt grid, 84 of them over a polygon that changed, so a `grid_key` saved from an earlier release must be mapped through this table, never matched by name: `prev_frac` is the weight that carries a per-cell value to the current cells. Keyed on (`prev_grid_key`, `grid_key`).",
      "provider": "calcofi",
      "dataset": "release"
    }
  },
  "columns": {
    "dataset.provider": {
      "name_long": "Provider",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.dataset": {
      "name_long": "Dataset",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.dataset_name": {
      "name_long": "Dataset Name",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.dataset_name_short": {
      "name_long": "Dataset Name Short",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.category": {
      "name_long": "Category",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.color": {
      "name_long": "Color",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.description": {
      "name_long": "Description",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.citation_main": {
      "name_long": "Citation Main",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.citation_others": {
      "name_long": "Citation Others",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.link_calcofi_org": {
      "name_long": "Link Calcofi Org",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.link_data_source": {
      "name_long": "Link Data Source",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.link_others": {
      "name_long": "Link Others",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.tables": {
      "name_long": "Tables",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.coverage_temporal": {
      "name_long": "Coverage Temporal",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.coverage_spatial": {
      "name_long": "Coverage Spatial",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.license": {
      "name_long": "License",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.pi_names": {
      "name_long": "Pi Names",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.doi": {
      "name_long": "Doi",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.license_url": {
      "name_long": "License Url",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.acknowledgement": {
      "name_long": "Acknowledgement",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset.contact": {
      "name_long": "Contact",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.ds_taxon_key": {
      "name_long": "Dataset Taxon Key",
      "description_md": "Key of this crosswalk row, `<dataset-or-known-list>:<local code>`.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "The dataset whose vocabulary this row belongs to.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "The global taxon it resolves to; joins `taxon`.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.ds_scientific_name": {
      "name_long": "Dataset Scientific Name",
      "description_md": "Scientific name as the source dataset spells it.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.ds_common_name": {
      "name_long": "Dataset Common Name",
      "description_md": "Common name as the source dataset spells it.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.ds_taxa_code": {
      "name_long": "Dataset Taxa Code",
      "description_md": "The dataset's own code, as stored on its measurement rows.",
      "data_type": "VARCHAR"
    },
    "dataset_taxon.ds_source_json": {
      "name_long": "Ds Source Json",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.measurement_type": {
      "name_long": "Measurement Type",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.description": {
      "name_long": "Description",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.units": {
      "name_long": "Units",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.valid_min": {
      "name_long": "Valid Min",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "measurement_type.valid_max": {
      "name_long": "Valid Max",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "measurement_type.valid_depth_min_m": {
      "name_long": "Valid Depth Min M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "measurement_type.valid_depth_max_m": {
      "name_long": "Valid Depth Max M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "measurement_type.derivation": {
      "name_long": "Derivation",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.is_canonical": {
      "name_long": "Is Canonical",
      "units": null,
      "description_md": "",
      "data_type": "BOOLEAN"
    },
    "measurement_type._source_column": {
      "name_long": " Source Column",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type._source_table": {
      "name_long": " Source Table",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type._source_datasets": {
      "name_long": " Source Datasets",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type._qual_column": {
      "name_long": " Qual Column",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type._prec_column": {
      "name_long": " Prec Column",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.grain": {
      "name_long": "Grain",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.denominator": {
      "name_long": "Denominator",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.category": {
      "name_long": "Category",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.variable": {
      "name_long": "Variable",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.nerc_p01": {
      "name_long": "Nerc P01",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.units_nerc_p06": {
      "name_long": "Units Nerc P06",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs.obs_id": {
      "name_long": "Observation ID",
      "description_md": "Surrogate key, renumbered globally when the release concatenates the per-dataset shards.",
      "data_type": "BIGINT"
    },
    "obs.realm": {
      "name_long": "Realm",
      "description_md": "`env` for physical/chemical measurements, `bio` for organism observations.",
      "data_type": "VARCHAR"
    },
    "obs.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "Provenance stamp: `provider_dataset`.",
      "data_type": "VARCHAR"
    },
    "obs.sample_key": {
      "name_long": "Sample Key",
      "description_md": "The sampling event this observation came from; joins `sample`.",
      "data_type": "VARCHAR"
    },
    "obs.grid_key": {
      "name_long": "Grid Key",
      "description_md": "CalCOFI station grid cell, denormalized from `sample` so rollups need no join. NULL for region-pooled data.",
      "data_type": "VARCHAR"
    },
    "obs.cruise_key": {
      "name_long": "Cruise Key",
      "description_md": "Cruise, denormalized from `sample` so rollups need no join.",
      "data_type": "VARCHAR"
    },
    "obs.latitude": {
      "name_long": "Latitude",
      "units": "decimal degrees",
      "description_md": "Observation latitude (WGS84).",
      "data_type": "DOUBLE"
    },
    "obs.longitude": {
      "name_long": "Longitude",
      "units": "decimal degrees",
      "description_md": "Observation longitude (WGS84).",
      "data_type": "DOUBLE"
    },
    "obs.datetime": {
      "name_long": "Datetime",
      "description_md": "Observation time (UTC). NULL for region-pooled data with no event time.",
      "data_type": "TIMESTAMP"
    },
    "obs.depth_min_m": {
      "name_long": "Depth Min",
      "units": "m",
      "description_md": "Shallowest depth this observation represents.",
      "data_type": "DOUBLE"
    },
    "obs.depth_max_m": {
      "name_long": "Depth Max",
      "units": "m",
      "description_md": "Deepest depth this observation represents; equal to `depth_min_m` for point measurements (bottle, CTD scan).",
      "data_type": "DOUBLE"
    },
    "obs.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "Global taxon key, `worms:<AphiaID>` or `itis:<TSN>` for birds. NULL for `env` rows. Joins `taxon`.",
      "data_type": "VARCHAR"
    },
    "obs.life_stage": {
      "name_long": "Life Stage",
      "description_md": "Life stage where the source resolves one (larva, adult, juvenile, egg, phyllosoma).",
      "data_type": "VARCHAR"
    },
    "obs.measurement_type": {
      "name_long": "Measurement Type",
      "description_md": "Measured quantity; joins the `measurement_type` vocabulary.",
      "data_type": "VARCHAR"
    },
    "obs.measurement_value": {
      "name_long": "Measurement Value",
      "description_md": "The measured value, in the units `measurement_type` declares.",
      "data_type": "DOUBLE"
    },
    "obs.measurement_qual": {
      "name_long": "Measurement Qualifier",
      "description_md": "Source quality flag, verbatim.",
      "data_type": "VARCHAR"
    },
    "obs.measurement_prec": {
      "name_long": "Measurement Precision",
      "description_md": "Source-reported precision where available.",
      "data_type": "DOUBLE"
    },
    "obs.hex_id": {
      "name_long": "Hex ID",
      "description_md": "H3 cell at resolution 10, stored as UBIGINT. Aggregate coarser at query time with `h3_cell_to_parent(hex_id, res)` — there is no per-resolution column ladder.",
      "data_type": "UBIGINT"
    },
    "sample.sample_key": {
      "name_long": "Sample Key",
      "description_md": "Globally unique event key, namespaced `dataset_key:sample_type:id` so the same integer id in two datasets — or at two event levels in one dataset — never collides.",
      "data_type": "VARCHAR"
    },
    "sample.sample_type": {
      "name_long": "Sample Type",
      "description_md": "Event grain: `site`, `tow`, `net`, `subsample`, `cast`, `bottle`, `water` (an eDNA water sample), `filter` (an eDNA water filter), `underway`, `transect` (a visual-survey effort segment), `sighting`, `deployment` (a sonobuoy), `scan` (one analysed hour of a recording) or `region_pool`.",
      "data_type": "VARCHAR"
    },
    "sample.parent_sample_key": {
      "name_long": "Parent Sample Key",
      "description_md": "The containing event (net → tow → site; bottle → cast; sighting → transect; scan → deployment). NULL at the top of the chain. Flat adjacency list: attributes are not inherited.",
      "data_type": "VARCHAR"
    },
    "sample.root_sample_key": {
      "name_long": "Root Sample Key",
      "description_md": "Top of this event's containment chain; equals `sample_key` for single-level datasets. Use `count(DISTINCT root_sample_key)` to count stations/casts irrespective of grain.",
      "data_type": "VARCHAR"
    },
    "sample.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "Provenance stamp: `provider_dataset`.",
      "data_type": "VARCHAR"
    },
    "sample.grid_key": {
      "name_long": "Grid Key",
      "description_md": "CalCOFI station grid cell. NULL where the dataset has no station assignment (region-pooled phytoplankton).",
      "data_type": "VARCHAR"
    },
    "sample.site_key": {
      "name_long": "Site Key",
      "description_md": "CalCOFI station natural key as the source records it (line/station, e.g. `090.0 060.0`). Present on 13 of the 18 source event tables, so it is carried on the event dimension rather than lost to consolidation; `grid_key` is the derived grid cell, this is the source's own station id.",
      "data_type": "VARCHAR"
    },
    "sample.cruise_key": {
      "name_long": "Cruise Key",
      "description_md": "CalCOFI cruise natural key `YYYY-MM-NODC`.",
      "data_type": "VARCHAR"
    },
    "sample.order_occ": {
      "name_long": "Order of Occupation",
      "description_md": "Order in which the station was occupied on the cruise. Source spelling varies (`order_occ`, `ord_occ`) and CTD stores it as text; normalised to an integer here.",
      "data_type": "INTEGER"
    },
    "sample.latitude": {
      "name_long": "Latitude",
      "units": "decimal degrees",
      "description_md": "Event latitude (WGS84).",
      "data_type": "DOUBLE"
    },
    "sample.longitude": {
      "name_long": "Longitude",
      "units": "decimal degrees",
      "description_md": "Event longitude (WGS84).",
      "data_type": "DOUBLE"
    },
    "sample.datetime": {
      "name_long": "Datetime",
      "description_md": "Event start time (UTC).",
      "data_type": "TIMESTAMP"
    },
    "sample.depth_min_m": {
      "name_long": "Depth Min",
      "units": "m",
      "description_md": "Shallowest depth sampled by this event.",
      "data_type": "DOUBLE"
    },
    "sample.depth_max_m": {
      "name_long": "Depth Max",
      "units": "m",
      "description_md": "Deepest depth sampled by this event; for swfsc_ichthyo tows and nets the maximum possible depth of the net (SWFSC Net.NetDepth, nominal: over a shallower sea floor the net did not reach it).",
      "data_type": "DOUBLE"
    },
    "sample.tow_type": {
      "name_long": "Tow Type",
      "description_md": "Net gear code where the dataset records one (C1/CB/CV/PV oblique or vertical, MT manta); NULL for gears and datasets without one. Needed to compute gear-appropriate CPUE.",
      "data_type": "VARCHAR"
    },
    "sample.data_stage": {
      "name_long": "Data Stage",
      "description_md": "The source's own processing state for this event: `final` (post-cruise calibrations applied) or `preliminary` (**not for publication** — the source warns that oxygen, nitrate and chlorophyll may change significantly once calibrated). Populated by `calcofi_ctd-cast`; NULL where the dataset draws no such distinction, which is not a claim that the data are final.",
      "data_type": "VARCHAR"
    },
    "sample.geom": {
      "name_long": "Geometry",
      "description_md": "Point geometry minted from `longitude`/`latitude` (OGC:CRS84).",
      "data_type": "GEOMETRY('EPSG:4326')"
    },
    "sample.source_uuid": {
      "name_long": "Source Uuid",
      "units": null,
      "description_md": "",
      "data_type": "UUID"
    },
    "sample_measurement.sample_measurement_id": {
      "name_long": "Sample Measurement ID",
      "description_md": "Surrogate key.",
      "data_type": "BIGINT"
    },
    "sample_measurement.sample_key": {
      "name_long": "Sample Key",
      "description_md": "The sampling event this effort measurement describes; joins `sample`.",
      "data_type": "VARCHAR"
    },
    "sample_measurement.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "Provenance stamp: `provider_dataset`.",
      "data_type": "VARCHAR"
    },
    "sample_measurement.measurement_type": {
      "name_long": "Measurement Type",
      "description_md": "Measured quantity; joins the `measurement_type` vocabulary.",
      "data_type": "VARCHAR"
    },
    "sample_measurement.measurement_value": {
      "name_long": "Measurement Value",
      "description_md": "The measured value, in the units `measurement_type` declares.",
      "data_type": "DOUBLE"
    },
    "sample_measurement.measurement_qual": {
      "name_long": "Measurement Qualifier",
      "description_md": "Source quality flag, verbatim.",
      "data_type": "VARCHAR"
    },
    "taxon.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "Global taxon key: lowercase authority prefix plus id, `worms:127023` or `itis:176754`.",
      "data_type": "VARCHAR"
    },
    "taxon.worms_id": {
      "name_long": "WoRMS ID",
      "description_md": "WoRMS AphiaID.",
      "data_type": "INTEGER"
    },
    "taxon.itis_id": {
      "name_long": "ITIS ID",
      "description_md": "ITIS Taxonomic Serial Number.",
      "data_type": "INTEGER"
    },
    "taxon.gbif_id": {
      "name_long": "GBIF ID",
      "description_md": "GBIF backbone taxon key.",
      "data_type": "INTEGER"
    },
    "taxon.ncbi_id": {
      "name_long": "NCBI ID",
      "description_md": "NCBI Taxonomy id.",
      "data_type": "INTEGER"
    },
    "taxon.inat_id": {
      "name_long": "iNaturalist ID",
      "description_md": "iNaturalist taxon id.",
      "data_type": "INTEGER"
    },
    "taxon.scientific_name": {
      "name_long": "Scientific Name",
      "description_md": "Accepted scientific name.",
      "data_type": "VARCHAR"
    },
    "taxon.common_name": {
      "name_long": "Common Name",
      "description_md": "Common name where one is recorded.",
      "data_type": "VARCHAR"
    },
    "taxon.rank": {
      "name_long": "Rank",
      "description_md": "Taxonomic rank.",
      "data_type": "VARCHAR"
    },
    "taxon.rank_order": {
      "name_long": "Rank Order",
      "description_md": "Ordinal for sorting ranks from kingdom down.",
      "data_type": "INTEGER"
    },
    "taxon.taxonomic_status": {
      "name_long": "Taxonomic Status",
      "description_md": "Status as fetched from the keying authority (accepted, unaccepted, superseded combination, ...). Read it with `status_checked` — before v2026.08.05 this column was the literal string \"accepted\" on every row, stamped rather than fetched.",
      "data_type": "VARCHAR"
    },
    "taxon.status_checked": {
      "name_long": "Status Checked",
      "description_md": "Date `taxonomic_status` was last confirmed against the authority. A status with no check date is not a fact.",
      "data_type": "VARCHAR"
    },
    "taxon.parent_taxon_key": {
      "name_long": "Parent Taxon Key",
      "description_md": "Lineage parent; walk this to expand a taxon to its descendants.",
      "data_type": "VARCHAR"
    },
    "taxon.kingdom": {
      "name_long": "Kingdom",
      "description_md": "Kingdom.",
      "data_type": "VARCHAR"
    },
    "taxon.phylum": {
      "name_long": "Phylum",
      "description_md": "Phylum.",
      "data_type": "VARCHAR"
    },
    "taxon.class": {
      "name_long": "Class",
      "description_md": "Class.",
      "data_type": "VARCHAR"
    },
    "taxon.order_taxon": {
      "name_long": "Order",
      "description_md": "Order (named `order_taxon` because `order` is a SQL keyword).",
      "data_type": "VARCHAR"
    },
    "taxon.family": {
      "name_long": "Family",
      "description_md": "Family.",
      "data_type": "VARCHAR"
    },
    "taxon.notes": {
      "name_long": "Notes",
      "description_md": "Append-only provenance log, one datestamped line per entry: how each id was resolved and any re-key onto an authority-accepted id (e.g. `itis:174553` Puffinus griseus -> `itis:1255050` Ardenna grisea). The dataset's own original code and name stay in `dataset_taxon`.",
      "data_type": "VARCHAR"
    },
    "measurement_type.provider": {
      "name_long": "Provider",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "measurement_type.dataset": {
      "name_long": "Dataset",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.obs_id": {
      "name_long": "Obs Id",
      "units": null,
      "description_md": "",
      "data_type": "BIGINT"
    },
    "obs_ctd_full.realm": {
      "name_long": "Realm",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.dataset_key": {
      "name_long": "Dataset Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.sample_key": {
      "name_long": "Sample Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.grid_key": {
      "name_long": "Grid Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.cruise_key": {
      "name_long": "Cruise Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.latitude": {
      "name_long": "Latitude",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.longitude": {
      "name_long": "Longitude",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.datetime": {
      "name_long": "Datetime",
      "units": null,
      "description_md": "",
      "data_type": "TIMESTAMP"
    },
    "obs_ctd_full.depth_min_m": {
      "name_long": "Depth Min M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.depth_max_m": {
      "name_long": "Depth Max M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.taxon_key": {
      "name_long": "Taxon Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.life_stage": {
      "name_long": "Life Stage",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.measurement_type": {
      "name_long": "Measurement Type",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.measurement_value": {
      "name_long": "Measurement Value",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.measurement_qual": {
      "name_long": "Measurement Qual",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_ctd_full.measurement_prec": {
      "name_long": "Measurement Prec",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_ctd_full.hex_id": {
      "name_long": "Hex Id",
      "units": null,
      "description_md": "",
      "data_type": "UBIGINT"
    },
    "obs_mets_full.obs_id": {
      "name_long": "Obs Id",
      "units": null,
      "description_md": "",
      "data_type": "BIGINT"
    },
    "obs_mets_full.realm": {
      "name_long": "Realm",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.dataset_key": {
      "name_long": "Dataset Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.sample_key": {
      "name_long": "Sample Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.grid_key": {
      "name_long": "Grid Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.cruise_key": {
      "name_long": "Cruise Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.latitude": {
      "name_long": "Latitude",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.longitude": {
      "name_long": "Longitude",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.datetime": {
      "name_long": "Datetime",
      "units": null,
      "description_md": "",
      "data_type": "TIMESTAMP"
    },
    "obs_mets_full.depth_min_m": {
      "name_long": "Depth Min M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.depth_max_m": {
      "name_long": "Depth Max M",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.taxon_key": {
      "name_long": "Taxon Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.life_stage": {
      "name_long": "Life Stage",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.measurement_type": {
      "name_long": "Measurement Type",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.measurement_value": {
      "name_long": "Measurement Value",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.measurement_qual": {
      "name_long": "Measurement Qual",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "obs_mets_full.measurement_prec": {
      "name_long": "Measurement Prec",
      "units": null,
      "description_md": "",
      "data_type": "DOUBLE"
    },
    "obs_mets_full.hex_id": {
      "name_long": "Hex Id",
      "units": null,
      "description_md": "",
      "data_type": "UBIGINT"
    },
    "obs_attribute.obs_attribute_id": {
      "name_long": "Observation Attribute ID",
      "description_md": "Surrogate key.",
      "data_type": "BIGINT"
    },
    "obs_attribute.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "Provenance stamp: `provider_dataset`.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.sample_key": {
      "name_long": "Sample Key",
      "description_md": "The sampling event; joins `sample`.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "Global taxon key; joins `taxon`.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.life_stage": {
      "name_long": "Life Stage",
      "description_md": "Life stage the attribution applies to.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.measurement_type": {
      "name_long": "Measurement Type",
      "description_md": "The attribute being broken down: `body_length`, `stage` or `behavior`.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.bin_value": {
      "name_long": "Bin Value",
      "description_md": "Numeric bin — length in mm, stage number. NULL for categorical attributes.",
      "data_type": "DOUBLE"
    },
    "obs_attribute.bin_label": {
      "name_long": "Bin Label",
      "description_md": "Category label — stage description, behavior name. NULL for purely numeric bins.",
      "data_type": "VARCHAR"
    },
    "obs_attribute.count": {
      "name_long": "Count",
      "units": "individuals",
      "description_md": "Number of individuals in this bin.",
      "data_type": "INTEGER"
    },
    "obs_attribute.measurement_qual": {
      "name_long": "Measurement Qualifier",
      "description_md": "Source quality flag, verbatim.",
      "data_type": "VARCHAR"
    },
    "region.region_key": {
      "name_long": "Region",
      "description_md": "Pooled-region code: NE, SE, Alley, or Offshore (primary key).",
      "data_type": "VARCHAR"
    },
    "region.description": {
      "name_long": "Description",
      "description_md": "Region description (Northern Inshore, Southern Inshore, California Current, Central Pacific).",
      "data_type": "VARCHAR"
    },
    "region.latitude": {
      "name_long": "Latitude",
      "units": "decimal degrees",
      "description_md": "Provisional region centroid latitude (mean of member CalCOFI stations; Q01).",
      "data_type": "DOUBLE"
    },
    "region.longitude": {
      "name_long": "Longitude",
      "units": "decimal degrees",
      "description_md": "Provisional region centroid longitude (mean of member CalCOFI stations; Q01).",
      "data_type": "DOUBLE"
    },
    "region.n_stations": {
      "name_long": "Number of Stations",
      "description_md": "Count of CalCOFI grid stations defining the region.",
      "data_type": "INTEGER"
    },
    "region.station_codes": {
      "name_long": "Station Codes",
      "description_md": "Member CalCOFI line.station codes (Hayward & Venrick 1998).",
      "data_type": "VARCHAR"
    },
    "region.geom": {
      "name_long": "Geom",
      "units": null,
      "description_md": "",
      "data_type": "GEOMETRY('EPSG:4326')"
    },
    "taxon_group.taxon_group_key": {
      "name_long": "Taxon Group Key",
      "description_md": "Group key, `<dataset-or-known-list>:<group>`.",
      "data_type": "VARCHAR"
    },
    "taxon_group.description": {
      "name_long": "Description",
      "description_md": "Human-readable description of the group.",
      "data_type": "VARCHAR"
    },
    "taxon_group.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "A member taxon; joins `taxon`.",
      "data_type": "VARCHAR"
    },
    "cruise.cruise_uuid": {
      "name_long": "Cruise Uuid",
      "units": null,
      "description_md": "CalCOFI species identifier, primary key in species table",
      "data_type": "UUID"
    },
    "cruise.date_ym": {
      "name_long": "Date Ym",
      "units": null,
      "description_md": "Cruise year and month — the YYYY-MM half of cruise_key.",
      "data_type": "DATE"
    },
    "cruise.ship_key": {
      "name_long": "Ship Key",
      "units": null,
      "description_md": "FK to ship; the natural key of the vessel that ran the cruise.",
      "data_type": "VARCHAR"
    },
    "cruise._source_file": {
      "name_long": " Source File",
      "units": null,
      "description_md": "Provenance: the source file this row was read from.",
      "data_type": "VARCHAR"
    },
    "cruise._source_row": {
      "name_long": " Source Row",
      "units": null,
      "description_md": "Provenance: 1-based row number within _source_file, so a value can be traced back to its line.",
      "data_type": "INTEGER"
    },
    "cruise._ingested_at": {
      "name_long": " Ingested At",
      "units": null,
      "description_md": "Provenance: UTC timestamp of the ingest run that produced this row.",
      "data_type": "TIMESTAMP"
    },
    "cruise._source_uuid": {
      "name_long": " Source Uuid",
      "units": null,
      "description_md": "Provenance: the UUID the source record carried where it minted one.",
      "data_type": "VARCHAR"
    },
    "cruise.cruise_key": {
      "name_long": "Cruise Key",
      "description_md": "Natural primary key in YYMMKK format (2-digit year + 2-digit month + ship_key)",
      "data_type": "VARCHAR"
    },
    "cruise.date_min": {
      "name_long": "Date Min",
      "units": null,
      "description_md": "",
      "data_type": "DATE"
    },
    "cruise.date_max": {
      "name_long": "Date Max",
      "units": null,
      "description_md": "",
      "data_type": "DATE"
    },
    "fish.sample_key": {
      "name_long": "Sample Key",
      "description_md": "The net (sample_type net) the fish were counted in; FK to sample.",
      "data_type": "VARCHAR"
    },
    "fish.species_id": {
      "name_long": "Species ID",
      "description_md": "CalCOFI species code (SWFSC SppCode); with sample_key the primary key. Its name is dataset_taxon.ds_scientific_name for ds_taxa_code = species_id.",
      "data_type": "INTEGER"
    },
    "fish.taxon_key": {
      "name_long": "Taxon Key",
      "description_md": "The taxon the species code resolves to (by its WoRMS AphiaID); FK to taxon.",
      "data_type": "VARCHAR"
    },
    "fish.tally": {
      "name_long": "Tally",
      "units": "count",
      "description_md": "Raw count of fish larger than larval size in the sorted portion of the net (not standardized; see the net's std_haul_factor and prop_sorted in sample_measurement). Additive to the larval abundance of the same net and species code.",
      "data_type": "INTEGER"
    },
    "grid.grid_key": {
      "name_long": "Grid Key",
      "description_md": "Natural primary key (e.g. st60-ln80 or st60-ln80_hist for historical)",
      "data_type": "VARCHAR"
    },
    "grid.station": {
      "name_long": "Station",
      "description_md": "Offshore component of CalCOFI coordinate system",
      "data_type": "DOUBLE"
    },
    "grid.line": {
      "name_long": "Line",
      "description_md": "Alongshore component of CalCOFI coordinate system",
      "data_type": "DOUBLE"
    },
    "grid.shore": {
      "name_long": "Shore",
      "description_md": "Shore classification (nearshore, offshore, etc.)",
      "data_type": "VARCHAR"
    },
    "grid.pattern": {
      "name_long": "Pattern",
      "description_md": "Station pattern: 'standard' or 'historical'",
      "data_type": "VARCHAR"
    },
    "grid.spacing": {
      "name_long": "Spacing",
      "description_md": "Station spacing in nautical miles",
      "data_type": "INTEGER"
    },
    "grid.zone": {
      "name_long": "Zone",
      "description_md": "Combined shore-pattern zone label",
      "data_type": "VARCHAR"
    },
    "grid.area_km2": {
      "name_long": "Area",
      "units": "km^2",
      "description_md": "Grid cell area",
      "data_type": "DOUBLE"
    },
    "grid.geom": {
      "name_long": "Geometry",
      "description_md": "Polygon geometry (WGS84 EPSG:4326) of grid cell",
      "data_type": "GEOMETRY('EPSG:4326')"
    },
    "grid.geom_ctr": {
      "name_long": "Geometry Center",
      "description_md": "Point geometry (WGS84 EPSG:4326) of grid cell centroid",
      "data_type": "GEOMETRY('EPSG:4326')"
    },
    "ichthyo_net.sample_key": {
      "name_long": "Sample Key",
      "description_md": "The net's sample_key (swfsc_ichthyo:net:<NetId>); primary key and FK to sample.",
      "data_type": "VARCHAR"
    },
    "ichthyo_net.net_uuid": {
      "name_long": "Net UUID",
      "description_md": "SWFSC's NetId, the provider's identifier of the net (= sample.source_uuid of the net row).",
      "data_type": "UUID"
    },
    "ichthyo_net.tow_uuid": {
      "name_long": "Tow UUID",
      "description_md": "SWFSC's TowId, the provider's identifier of the tow the net was on (= sample.source_uuid of the net's parent tow row).",
      "data_type": "UUID"
    },
    "ichthyo_net.net_side": {
      "name_long": "Net Side",
      "description_md": "Side of a bongo pair the net was on: S (starboard) or P (port) on CalBOBL (CB) and PairoVET (PV) tows; NULL on the single-net C1, CalVET (CV) and Manta (MT) tows. Zooplankton volume is measured on the starboard net only.",
      "data_type": "VARCHAR"
    },
    "ichthyo_net.tow_number": {
      "name_long": "Tow Number",
      "description_md": "Which of several tows of one type at one station occupation this net's tow is (SWFSC TowNumber): 1 for all but 121 of 74,385 tows, up to 50. (site, tow type, tow number) is unique.",
      "data_type": "SMALLINT"
    },
    "ichthyo_net.tow_type": {
      "name_long": "Tow Type",
      "description_md": "The tow's gear code (C1, CB, CV, MT, PV), as on sample.tow_type; see gear.csv.",
      "data_type": "VARCHAR"
    },
    "lookup.lookup_id": {
      "name_long": "Lookup ID",
      "description_md": "Sequential integer primary key",
      "data_type": "INTEGER"
    },
    "lookup.lookup_type": {
      "name_long": "Lookup Type",
      "description_md": "Category: 'egg_stage', 'larva_stage', or 'tow_type'",
      "data_type": "VARCHAR"
    },
    "lookup.lookup_num": {
      "name_long": "Lookup Number",
      "description_md": "Numeric code for the lookup value",
      "data_type": "INTEGER"
    },
    "lookup.lookup_chr": {
      "name_long": "Lookup Character",
      "description_md": "Character code for the lookup value (e.g. YOLK, PREF)",
      "data_type": "VARCHAR"
    },
    "lookup.description": {
      "name_long": "Description",
      "description_md": "Human-readable description of the lookup value",
      "data_type": "VARCHAR"
    },
    "lookup._source_file": {
      "name_long": " Source File",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "lookup._source_row": {
      "name_long": " Source Row",
      "units": null,
      "description_md": "",
      "data_type": "INTEGER"
    },
    "lookup._ingested_at": {
      "name_long": " Ingested At",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "lookup._source_uuid": {
      "name_long": " Source Uuid",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "ship.ship_key": {
      "name_long": "Ship Key",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "ship.ship_name": {
      "name_long": "Ship Name",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "ship.ship_nodc": {
      "name_long": "Ship Nodc",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "ship.ship_ices": {
      "name_long": "Ship Ices",
      "units": null,
      "description_md": "ICES platform code of the ship, beside the NODC code that keys cruise_key (swfsc_ichthyo_14)",
      "data_type": "VARCHAR"
    },
    "ship._source_file": {
      "name_long": " Source File",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "ship._source_row": {
      "name_long": " Source Row",
      "units": null,
      "description_md": "",
      "data_type": "INTEGER"
    },
    "ship._ingested_at": {
      "name_long": " Ingested At",
      "units": null,
      "description_md": "",
      "data_type": "TIMESTAMP"
    },
    "ship._source_uuid": {
      "name_long": " Source Uuid",
      "units": null,
      "description_md": "",
      "data_type": "VARCHAR"
    },
    "cruise.year": {
      "name_long": "Year",
      "units": null,
      "description_md": "Cruise year extracted from date_ym.",
      "data_type": "INTEGER"
    },
    "cruise.month": {
      "name_long": "Month",
      "units": null,
      "description_md": "Cruise month extracted from date_ym.",
      "data_type": "INTEGER"
    },
    "cruise.ship_name": {
      "name_long": "Ship Name",
      "units": null,
      "description_md": "Ship name as resolved against NODC ship registry.",
      "data_type": "VARCHAR"
    },
    "cruise.ship_nodc": {
      "name_long": "Ship NODC",
      "units": null,
      "description_md": "NODC ship code.",
      "data_type": "VARCHAR"
    },
    "cruise.ship_ices": {
      "name_long": "Ship ICES",
      "units": null,
      "description_md": "ICES platform code of the ship (SWFSC ShipLookup), beside the NODC code that keys cruise_key; NULL for a ship no SWFSC cruise used.",
      "data_type": "VARCHAR"
    },
    "cruise.ichthyo": {
      "name_long": "Ichthyo Sites",
      "units": "count",
      "description_md": "Distinct sites sampled by SWFSC ichthyo on this cruise.",
      "data_type": "BIGINT"
    },
    "cruise.bottle": {
      "name_long": "Bottle Sites",
      "units": "count",
      "description_md": "Distinct sites sampled by CalCOFI bottle casts on this cruise.",
      "data_type": "BIGINT"
    },
    "cruise.ctd_cast": {
      "name_long": "CTD Sites",
      "units": "count",
      "description_md": "Distinct sites sampled by CTD casts on this cruise.",
      "data_type": "BIGINT"
    },
    "cruise.dic": {
      "name_long": "DIC Sites",
      "units": "count",
      "description_md": "Distinct sites with NCEI DIC samples on this cruise.",
      "data_type": "BIGINT"
    },
    "spatial.spatial_key": {
      "name_long": "Spatial Key",
      "units": null,
      "description_md": "Primary key, `layer:id` (e.g. `ca_county_boundaries:1`). Join `spatial_attribute` on THIS, not on `id` — `id` is per-layer sequential, so a county and a sanctuary both have id 1 and joining on it alone silently mixes layers.",
      "data_type": "VARCHAR"
    },
    "spatial.id": {
      "name_long": "Feature ID",
      "units": null,
      "description_md": "Per-layer sequential integer feature id. Kept because it is still meaningful within a layer; it is NOT unique across the table.",
      "data_type": "INTEGER"
    },
    "spatial.layer": {
      "name_long": "Layer",
      "units": null,
      "description_md": "Spatial layer slug from metadata/spatial_layers.csv (e.g. ca_county_boundaries).",
      "data_type": "VARCHAR"
    },
    "spatial.name": {
      "name_long": "Name",
      "units": null,
      "description_md": "Per-feature label taken from the layer's name_field, or the layer name itself for dissolved layers.",
      "data_type": "VARCHAR"
    },
    "spatial.geom": {
      "name_long": "Geometry",
      "units": null,
      "description_md": "Feature geometry in WGS84 (EPSG:4326).",
      "data_type": "GEOMETRY('EPSG:4326')"
    },
    "spatial_attribute.spatial_key": {
      "name_long": "Spatial Key",
      "units": null,
      "description_md": "FK to spatial.spatial_key — the feature this attribute belongs to.",
      "data_type": "VARCHAR"
    },
    "spatial_attribute.id": {
      "name_long": "Feature ID",
      "units": null,
      "description_md": "Per-layer feature id matching spatial.id within the same layer. Redundant with spatial_key; kept for readability.",
      "data_type": "INTEGER"
    },
    "spatial_attribute.layer": {
      "name_long": "Layer",
      "units": null,
      "description_md": "Spatial layer slug matching spatial.layer.",
      "data_type": "VARCHAR"
    },
    "spatial_attribute.fld": {
      "name_long": "Field",
      "units": null,
      "description_md": "Name of the source attribute column this row carries. The table is entity-attribute-value — one row per (feature, source column) — so layers with entirely unrelated attribute schemas share one table.",
      "data_type": "VARCHAR"
    },
    "spatial_attribute.val_dbl": {
      "name_long": "Value (double)",
      "units": null,
      "description_md": "Value when the source column was numeric; NULL otherwise. Exactly ONE val_* column is populated per row, chosen by the source column's R type, so read the one matching fld or COALESCE across them as text.",
      "data_type": "DOUBLE"
    },
    "spatial_attribute.val_int": {
      "name_long": "Value (integer)",
      "units": null,
      "description_md": "Value when the source column was integer; NULL otherwise.",
      "data_type": "INTEGER"
    },
    "spatial_attribute.val_chr": {
      "name_long": "Value (text)",
      "units": null,
      "description_md": "Value when the source column was character or factor; NULL otherwise. Also the fallback for any type with no dedicated column.",
      "data_type": "VARCHAR"
    },
    "spatial_attribute.val_date": {
      "name_long": "Value (date)",
      "units": null,
      "description_md": "Value when the source column was a Date; NULL otherwise.",
      "data_type": "DATE"
    },
    "spatial_attribute.val_lgl": {
      "name_long": "Value (logical)",
      "units": null,
      "description_md": "Value when the source column was logical; NULL otherwise.",
      "data_type": "BOOLEAN"
    },
    "sample_root.root_id": {
      "name_long": "Root ID",
      "units": null,
      "description_md": "Dense integer id of a root sampling event (`sample` with no parent), numbered deterministically over `sample_key`; the join key shared by `obs_bio`, `obs_env` and `sample_spatial`.",
      "data_type": "INTEGER"
    },
    "sample_root.root_sample_key": {
      "name_long": "Root Sample Key",
      "units": null,
      "description_md": "The `sample.sample_key` this root id stands for.",
      "data_type": "VARCHAR"
    },
    "sample_root.seafloor_depth_m": {
      "name_long": "Seafloor Depth",
      "units": "m",
      "description_md": "GEBCO seafloor depth at the root sample's position (positive down), from `sample`.",
      "data_type": "DOUBLE"
    },
    "sample_root.hex7": {
      "name_long": "H3 Cell (res 7)",
      "units": null,
      "description_md": "The root sample's own `sample.hex7`, carried unchanged: one `UBIGINT` H3 cell at resolution 7, the parent of the resolution-10 cell of the root's position; NULL without a finite position. Coarser parents are bit arithmetic (`calcofi4db::h3_parent_sql()`), no extension needed.",
      "data_type": "UBIGINT"
    },
    "sample.hex7": {
      "name_long": "H3 Cell (res 7)",
      "units": null,
      "description_md": "One `UBIGINT` H3 cell at resolution 7: the parent of the resolution-10 cell of this event's own `latitude` / `longitude` (not the resolution-7 cell the position falls in), defined exactly as `obs_bio.hex7` / `obs_env.hex7`; NULL without a finite position. Lets a per-sample value in `sample_measurement` be drawn in hexagons. An observation carries its own position, so a CTD scan can sit in another cell than its cast.",
      "data_type": "UBIGINT"
    },
    "sample_spatial.root_id": {
      "name_long": "Root ID",
      "units": null,
      "description_md": "Root sampling event (`sample_root.root_id`).",
      "data_type": "INTEGER"
    },
    "sample_spatial.root_sample_key": {
      "name_long": "Root Sample Key",
      "units": null,
      "description_md": "The root `sample.sample_key`.",
      "data_type": "VARCHAR"
    },
    "sample_spatial.layer": {
      "name_long": "Layer",
      "units": null,
      "description_md": "Spatial layer name (`spatial.layer`); polygon layers only — boundary lines and ports never hold a sample.",
      "data_type": "VARCHAR"
    },
    "sample_spatial.spatial_key": {
      "name_long": "Spatial Key",
      "units": null,
      "description_md": "The polygon (`spatial.spatial_key`) the root sample's position falls in; exact `ST_Intersects`, computed once at release.",
      "data_type": "VARCHAR"
    },
    "sample_spatial.spatial_name": {
      "name_long": "Spatial Name",
      "units": null,
      "description_md": "Display name of the polygon (`spatial.name`).",
      "data_type": "VARCHAR"
    },
    "obs_bio.obs_id": {
      "name_long": "Observation ID",
      "units": null,
      "description_md": "`obs.obs_id` — the row this slim copy stands for.",
      "data_type": "BIGINT"
    },
    "obs_env.obs_id": {
      "name_long": "Observation ID",
      "units": null,
      "description_md": "`obs.obs_id` — the row this slim copy stands for.",
      "data_type": "BIGINT"
    },
    "obs_bio.root_id": {
      "name_long": "Root ID",
      "units": null,
      "description_md": "Root sampling event (`sample_root.root_id`).",
      "data_type": "INTEGER"
    },
    "obs_env.root_id": {
      "name_long": "Root ID",
      "units": null,
      "description_md": "Root sampling event (`sample_root.root_id`).",
      "data_type": "INTEGER"
    },
    "obs_bio.year": {
      "name_long": "Year",
      "units": null,
      "description_md": "Calendar year of `datetime`.",
      "data_type": "SMALLINT"
    },
    "obs_env.year": {
      "name_long": "Year",
      "units": null,
      "description_md": "Calendar year of `datetime`.",
      "data_type": "SMALLINT"
    },
    "obs_bio.quarter": {
      "name_long": "Quarter",
      "units": null,
      "description_md": "Calendar quarter (1–4) of `datetime`.",
      "data_type": "TINYINT"
    },
    "obs_env.quarter": {
      "name_long": "Quarter",
      "units": null,
      "description_md": "Calendar quarter (1–4) of `datetime`.",
      "data_type": "TINYINT"
    },
    "obs_bio.depth_bin": {
      "name_long": "Depth Bin",
      "units": "m",
      "description_md": "`floor(depth_min_m / 10) * 10`; the observation's depth, falling back to its sample's and its root's.",
      "data_type": "INTEGER"
    },
    "obs_env.depth_bin": {
      "name_long": "Depth Bin",
      "units": "m",
      "description_md": "`floor(depth_min_m / 10) * 10`; the observation's depth, falling back to its sample's and its root's.",
      "data_type": "INTEGER"
    },
    "obs_bio.units": {
      "name_long": "Units",
      "units": null,
      "description_md": "`measurement_type.units` of `value`.",
      "data_type": "VARCHAR"
    },
    "obs_env.units": {
      "name_long": "Units",
      "units": null,
      "description_md": "`measurement_type.units` of `value`.",
      "data_type": "VARCHAR"
    },
    "obs_bio.value": {
      "name_long": "Value",
      "units": null,
      "description_md": "`obs.measurement_value`.",
      "data_type": "DOUBLE"
    },
    "obs_env.value": {
      "name_long": "Value",
      "units": null,
      "description_md": "`obs.measurement_value`.",
      "data_type": "DOUBLE"
    },
    "obs_bio.qual_ok": {
      "name_long": "Quality OK",
      "units": null,
      "description_md": "`calcofi4r::cc_qual_ok_sql()` evaluated at release: FALSE for a dataset's own bad/missing codes (bottle & CTD 8, 9; DIC 3, 4, 9), TRUE otherwise, NULL never.",
      "data_type": "BOOLEAN"
    },
    "obs_env.qual_ok": {
      "name_long": "Quality OK",
      "units": null,
      "description_md": "`calcofi4r::cc_qual_ok_sql()` evaluated at release: FALSE for a dataset's own bad/missing codes (bottle & CTD 8, 9; DIC 3, 4, 9), TRUE otherwise, NULL never.",
      "data_type": "BOOLEAN"
    },
    "obs_bio.tow_type": {
      "name_long": "Tow Type",
      "units": null,
      "description_md": "Gear of the observation's own sample (`sample.tow_type`: C1/CB/CV/PV oblique–vertical, MT manta).",
      "data_type": "VARCHAR"
    },
    "obs_env.tow_type": {
      "name_long": "Tow Type",
      "units": null,
      "description_md": "Gear of the observation's own sample (`sample.tow_type`: C1/CB/CV/PV oblique–vertical, MT manta).",
      "data_type": "VARCHAR"
    },
    "obs_bio.std_haul_factor": {
      "name_long": "Standard Haul Factor",
      "units": null,
      "description_md": "Effort of the observation's own sample (`sample_measurement`).",
      "data_type": "DOUBLE"
    },
    "obs_env.std_haul_factor": {
      "name_long": "Standard Haul Factor",
      "units": null,
      "description_md": "Effort of the observation's own sample (`sample_measurement`).",
      "data_type": "DOUBLE"
    },
    "obs_bio.prop_sorted": {
      "name_long": "Proportion Sorted",
      "units": null,
      "description_md": "Effort of the observation's own sample (`sample_measurement`); 0 or NULL means all of it was sorted.",
      "data_type": "DOUBLE"
    },
    "obs_env.prop_sorted": {
      "name_long": "Proportion Sorted",
      "units": null,
      "description_md": "Effort of the observation's own sample (`sample_measurement`); 0 or NULL means all of it was sorted.",
      "data_type": "DOUBLE"
    },
    "obs_bio.volume_sampled_m3": {
      "name_long": "Volume Sampled",
      "units": "m3",
      "description_md": "Effort of the observation's own sample (`sample_measurement.volume_sampled`).",
      "data_type": "DOUBLE"
    },
    "obs_env.volume_sampled_m3": {
      "name_long": "Volume Sampled",
      "units": "m3",
      "description_md": "Effort of the observation's own sample (`sample_measurement.volume_sampled`).",
      "data_type": "DOUBLE"
    },
    "obs_bio.density_per_10m2": {
      "name_long": "Density per 10 m²",
      "units": "count/10m2",
      "description_md": "Areal, depth-integrated: `count × std_haul_factor / prop_sorted` for C1/CB/CV/PV tows, published per-m² × 10; NULL where the effort is not in the release (`calcofi4r::cc_density_sql()`).",
      "data_type": "DOUBLE"
    },
    "obs_env.density_per_10m2": {
      "name_long": "Density per 10 m²",
      "units": "count/10m2",
      "description_md": "Areal, depth-integrated: `count × std_haul_factor / prop_sorted` for C1/CB/CV/PV tows, published per-m² × 10; NULL where the effort is not in the release (`calcofi4r::cc_density_sql()`).",
      "data_type": "DOUBLE"
    },
    "obs_bio.density_per_1000m3": {
      "name_long": "Density per 1000 m³",
      "units": "count/1000m3",
      "description_md": "Volumetric: `count / prop_sorted / volume_sampled_m3 × 1000` for any tow with a volume, published per-1000 m³ as is; never converted from the areal density.",
      "data_type": "DOUBLE"
    },
    "obs_env.density_per_1000m3": {
      "name_long": "Density per 1000 m³",
      "units": "count/1000m3",
      "description_md": "Volumetric: `count / prop_sorted / volume_sampled_m3 × 1000` for any tow with a volume, published per-1000 m³ as is; never converted from the areal density.",
      "data_type": "DOUBLE"
    },
    "obs_bio.effort_class": {
      "name_long": "Effort Class",
      "units": null,
      "description_md": "`count_with_effort` | `raw_count_no_effort` | `density_as_published` | `other_unit` — what the row can be standardized to; rows without effort are an ingest task, not a UI caveat.",
      "data_type": "VARCHAR"
    },
    "obs_env.effort_class": {
      "name_long": "Effort Class",
      "units": null,
      "description_md": "`count_with_effort` | `raw_count_no_effort` | `density_as_published` | `other_unit` — what the row can be standardized to; rows without effort are an ingest task, not a UI caveat.",
      "data_type": "VARCHAR"
    },
    "obs_bio.hex7": {
      "name_long": "H3 Cell (res 7)",
      "units": null,
      "description_md": "One `UBIGINT` H3 cell at resolution 7 (parent of `hex_id`); coarser parents are bit arithmetic (`calcofi4db::h3_parent_sql()`), no extension needed.",
      "data_type": "UBIGINT"
    },
    "obs_env.hex7": {
      "name_long": "H3 Cell (res 7)",
      "units": null,
      "description_md": "One `UBIGINT` H3 cell at resolution 7 (parent of `hex_id`); coarser parents are bit arithmetic (`calcofi4db::h3_parent_sql()`), no extension needed.",
      "data_type": "UBIGINT"
    },
    "obs_bio.sample_key": {
      "name_long": "Sample Key",
      "units": null,
      "description_md": "The observation's own sampling event (`sample.sample_key`, namespaced `dataset:type:id`) — the net or tow, not just the root (`root_id`); `sample_measurement` and `obs_attribute` join on it.",
      "data_type": "VARCHAR"
    },
    "obs_env.sample_key": {
      "name_long": "Sample Key",
      "units": null,
      "description_md": "The observation's own sampling event (`sample.sample_key`, namespaced `dataset:type:id`) — the bottle or cast, not just the root (`root_id`).",
      "data_type": "VARCHAR"
    },
    "obs_bio.measurement_prec": {
      "name_long": "Measurement Precision",
      "units": null,
      "description_md": "Precision of `value` as the source reports it (`obs.measurement_prec`); NULL where the source states none.",
      "data_type": "DOUBLE"
    },
    "obs_env.measurement_prec": {
      "name_long": "Measurement Precision",
      "units": null,
      "description_md": "Precision of `value` as the source reports it (`obs.measurement_prec`); NULL where the source states none.",
      "data_type": "DOUBLE"
    },
    "obs_bio.hex_id": {
      "name_long": "H3 Cell (res 10)",
      "units": null,
      "description_md": "The `UBIGINT` H3 cell at `CC_H3_RES_MAX` (resolution 10) of the observation's position, as on `obs`; `hex7` is its resolution-7 parent.",
      "data_type": "UBIGINT"
    },
    "obs_env.hex_id": {
      "name_long": "H3 Cell (res 10)",
      "units": null,
      "description_md": "The `UBIGINT` H3 cell at `CC_H3_RES_MAX` (resolution 10) of the observation's position, as on `obs`; `hex7` is its resolution-7 parent.",
      "data_type": "UBIGINT"
    },
    "climatology.dataset_key": {
      "name_long": "Dataset Key",
      "units": null,
      "description_md": "Dataset the baseline is built from (`dataset.dataset_key`); one row per dataset so a CTD-only consumer filters and a cross-dataset one pools weighted by `clim_n` (`sum(clim_mean * clim_n) / sum(clim_n)` is exactly the mean over the pooled observations).",
      "data_type": "VARCHAR"
    },
    "climatology.grid_key": {
      "name_long": "Grid Key",
      "units": null,
      "description_md": "CalCOFI grid cell (`grid.grid_key`) most of the station's observations fall in: its modal cell. The baseline is keyed on the station (`site_key`), not on the cell; since the grid was rebuilt from the official station positions an official station has a cell of its own.",
      "data_type": "VARCHAR"
    },
    "climatology.month": {
      "name_long": "Month",
      "units": null,
      "description_md": "Calendar month 1–12 of the observations' `datetime`. The anomaly of a cast is its value minus the cell of the cast's own calendar month.",
      "data_type": "TINYINT"
    },
    "climatology.depth_bin": {
      "name_long": "Depth Bin",
      "units": "m",
      "description_md": "10 m floor bin of `obs.depth_min_m` (`floor(depth_min_m / 10) * 10`, the `obs_env.depth_bin` convention), labelled by its shallow edge; 0–500.",
      "data_type": "INTEGER"
    },
    "climatology.measurement_type": {
      "name_long": "Measurement Type",
      "units": null,
      "description_md": "The measured quantity (`measurement_type.measurement_type`); the table's partition column.",
      "data_type": "VARCHAR"
    },
    "climatology.clim_mean": {
      "name_long": "Climatological Mean",
      "units": null,
      "description_md": "Mean of the quality-passing (`cc_qual_ok_sql()`) finite values in the cell over `clim_yr_min`–`clim_yr_max`; in the type's own units.",
      "data_type": "DOUBLE"
    },
    "climatology.clim_sd": {
      "name_long": "Climatological SD",
      "units": null,
      "description_md": "Sample standard deviation of the same values; NULL when `clim_n` = 1. `anomaly / clim_sd` expresses a departure in baseline standard deviations.",
      "data_type": "DOUBLE"
    },
    "climatology.clim_n": {
      "name_long": "N Observations",
      "units": null,
      "description_md": "Observations in the cell.",
      "data_type": "INTEGER"
    },
    "climatology.n_cruises": {
      "name_long": "N Cruises",
      "units": null,
      "description_md": "Distinct cruises in the cell; a cell needs at least 3 to exist.",
      "data_type": "INTEGER"
    },
    "climatology.clim_yr_min": {
      "name_long": "Window Start",
      "units": null,
      "description_md": "First year of the baseline window (inclusive); stamped on every row so the parquet alone says what the mean is a mean of.",
      "data_type": "SMALLINT"
    },
    "climatology.clim_yr_max": {
      "name_long": "Window End",
      "units": null,
      "description_md": "Last year of the baseline window (inclusive).",
      "data_type": "SMALLINT"
    },
    "grid_crosswalk.prev_grid_key": {
      "name_long": "Previous Grid Key",
      "units": null,
      "description_md": "Key of a cell of the previous CalCOFI grid (`calcofi4r::cc_grid_v1`, the grid of every release through v2026.10.01). Not a foreign key: the previous grid is not released. 196 of the 218 previous keys are also keys of this release's grid, 84 of them over a polygon that changed, so never match it to `grid_key` by name.",
      "data_type": "VARCHAR"
    },
    "grid_crosswalk.grid_key": {
      "name_long": "Grid Key",
      "units": null,
      "description_md": "Key of a cell of this release's grid (`grid.grid_key`) that overlaps the previous cell.",
      "data_type": "VARCHAR"
    },
    "grid_crosswalk.overlap_km2": {
      "name_long": "Overlap Area",
      "units": "km2",
      "description_md": "Area the two cells share, in California Albers (EPSG:3310), rounded to the square metre.",
      "data_type": "DOUBLE"
    },
    "grid_crosswalk.prev_frac": {
      "name_long": "Share of the Previous Cell",
      "units": null,
      "description_md": "`overlap_km2` as a fraction of the previous cell's whole area: the weight that carries a value keyed on the previous grid to the current cells (`sum(value * prev_frac)` per `grid_key`). Sums over a previous cell to one, less the part of it no current cell covers (land under the finer coastline); never rescaled.",
      "data_type": "DOUBLE"
    },
    "grid_crosswalk.grid_frac": {
      "name_long": "Share of the Current Cell",
      "units": null,
      "description_md": "`overlap_km2` as a fraction of the current cell's whole area. Sums over a current cell to one, less the part no previous cell covered; slightly over one for seven cells along the line 93.3 / line 100 boundary, where previous cells overlap each other.",
      "data_type": "DOUBLE"
    },
    "climatology.site_key": {
      "data_type": "VARCHAR"
    },
    "climatology.quarter": {
      "data_type": "TINYINT"
    },
    "climatology.season_mean": {
      "data_type": "DOUBLE"
    },
    "climatology.season_sd": {
      "data_type": "DOUBLE"
    },
    "climatology.season_n": {
      "data_type": "INTEGER"
    },
    "climatology.season_n_cruises": {
      "data_type": "INTEGER"
    },
    "cruise.cruise_key_method": {
      "data_type": "VARCHAR"
    },
    "cruise.cruise_key_datasets": {
      "data_type": "VARCHAR"
    },
    "dataset.dataset_key": {
      "data_type": "VARCHAR"
    },
    "dataset.source_accessed": {
      "data_type": "DATE"
    },
    "dataset.source_accessed_method": {
      "data_type": "VARCHAR"
    },
    "obs_bio.dataset_key": {
      "data_type": "VARCHAR"
    },
    "obs_bio.grid_key": {
      "data_type": "VARCHAR"
    },
    "obs_bio.site_key": {
      "data_type": "VARCHAR"
    },
    "obs_bio.cruise_key": {
      "data_type": "VARCHAR"
    },
    "obs_bio.latitude": {
      "data_type": "DOUBLE"
    },
    "obs_bio.longitude": {
      "data_type": "DOUBLE"
    },
    "obs_bio.datetime": {
      "data_type": "TIMESTAMP"
    },
    "obs_bio.depth_min_m": {
      "data_type": "DOUBLE"
    },
    "obs_bio.depth_max_m": {
      "data_type": "DOUBLE"
    },
    "obs_bio.taxon_key": {
      "data_type": "VARCHAR"
    },
    "obs_bio.life_stage": {
      "data_type": "VARCHAR"
    },
    "obs_bio.measurement_type": {
      "data_type": "VARCHAR"
    },
    "obs_bio.measurement_qual": {
      "data_type": "VARCHAR"
    },
    "obs_env.dataset_key": {
      "data_type": "VARCHAR"
    },
    "obs_env.grid_key": {
      "data_type": "VARCHAR"
    },
    "obs_env.site_key": {
      "data_type": "VARCHAR"
    },
    "obs_env.cruise_key": {
      "data_type": "VARCHAR"
    },
    "obs_env.latitude": {
      "data_type": "DOUBLE"
    },
    "obs_env.longitude": {
      "data_type": "DOUBLE"
    },
    "obs_env.datetime": {
      "data_type": "TIMESTAMP"
    },
    "obs_env.depth_min_m": {
      "data_type": "DOUBLE"
    },
    "obs_env.depth_max_m": {
      "data_type": "DOUBLE"
    },
    "obs_env.taxon_key": {
      "data_type": "VARCHAR"
    },
    "obs_env.life_stage": {
      "data_type": "VARCHAR"
    },
    "obs_env.measurement_type": {
      "data_type": "VARCHAR"
    },
    "obs_env.measurement_qual": {
      "data_type": "VARCHAR"
    },
    "sample.seafloor_depth_m": {
      "data_type": "DOUBLE"
    },
    "sample.station_uuid": {
      "data_type": "UUID"
    },
    "sample.station_uuid_method": {
      "data_type": "VARCHAR"
    },
    "sample_root.dataset_key": {
      "data_type": "VARCHAR"
    },
    "sample_root.sample_type": {
      "data_type": "VARCHAR"
    },
    "sample_root.grid_key": {
      "data_type": "VARCHAR"
    },
    "sample_root.cruise_key": {
      "data_type": "VARCHAR"
    },
    "sample_root.order_occ": {
      "data_type": "INTEGER"
    },
    "sample_root.latitude": {
      "data_type": "DOUBLE"
    },
    "sample_root.longitude": {
      "data_type": "DOUBLE"
    },
    "sample_root.datetime": {
      "data_type": "TIMESTAMP"
    },
    "sample_root.depth_min_m": {
      "data_type": "DOUBLE"
    },
    "sample_root.depth_max_m": {
      "data_type": "DOUBLE"
    },
    "sample_root.tow_type": {
      "data_type": "VARCHAR"
    }
  },
  "measurement_types": {
    "abundance": {
      "description": "Specimen count per net tow (headline occurrence; standardize via std_haul_factor)",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "calcofi_phyllosoma",
        "cdfw_dungeness-crab",
        "sio_mesopelagic-fish",
        "swfsc_cufes",
        "swfsc_ichthyo"
      ]
    },
    "acoustic_presence": {
      "description": "Presence (1) or absence (0) of the taxon's calls in one hour of sonobuoy recording, scanned as 60-s spectrogram windows (headline occurrence; the call types heard are obs_attribute call_type)",
      "units": "dimensionless",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 1,
      "datasets": [
        "sio_cetacean-sonobuoy"
      ]
    },
    "air_temp_c": {
      "description": "Air temperature",
      "units": "deg_C",
      "is_canonical": true,
      "valid_min": -50,
      "valid_max": 60,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "alkalinity": {
      "description": "Total alkalinity",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 5000,
      "datasets": [
        "calcofi_dic"
      ]
    },
    "alkalinity_rep1": {
      "description": "Total alkalinity replicate 1",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 5000,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "alkalinity_rep2": {
      "description": "Total alkalinity replicate 2",
      "units": "umol/kg",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "ammonia": {
      "description": "Ammonium concentration (QC'd; the source column is named NH3)",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 100,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_bottle"
      ]
    },
    "anchovy_eggs": {
      "description": "Northern anchovy egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "atm_pressure_mb": {
      "description": "Atmospheric pressure (ship level)",
      "units": "mb",
      "is_canonical": true,
      "valid_min": 800,
      "valid_max": 1100,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "atm_pressure_slc_mb": {
      "description": "Atmospheric pressure (sea-level corrected)",
      "units": "mb",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "barometric_pressure": {
      "description": "Barometric pressure",
      "units": "millibars",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "beam_attenuation": {
      "description": "Beam attenuation coefficient",
      "units": "1/m",
      "is_canonical": true,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "behavior": {
      "description": "Seabird/marine-mammal behavior category (obs_attribute; e.g. Flying, Feeding)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "farallon_bird-mammal"
      ]
    },
    "body_length": {
      "description": "Larva body length (obs_freq binned attribute)",
      "units": "mm",
      "is_canonical": true,
      "datasets": [
        "swfsc_ichthyo"
      ]
    },
    "bottom_depth": {
      "description": "Water depth at the sampling event (sea floor depth beneath the cast)",
      "units": "m",
      "is_canonical": false,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "bottom_depth_m": {
      "description": "Bottom depth (single-beam)",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 11000,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "bottom_depth_mb_m": {
      "description": "Bottom depth (multibeam)",
      "units": "m",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "btl_ammonium": {
      "description": "Bottle ammonium",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 100,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_chlorophyll_a": {
      "description": "Bottle chlorophyll-a",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": -1,
      "valid_max": 100,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_depth": {
      "description": "Bottle trip depth",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 11000,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_nitrate": {
      "description": "Bottle nitrate",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 100,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_nitrite": {
      "description": "Bottle nitrite",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_phaeopigment": {
      "description": "Bottle phaeopigment",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": -5,
      "valid_max": 100,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_phosphate": {
      "description": "Bottle phosphate",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_silicate": {
      "description": "Bottle silicate",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 300,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "btl_temperature": {
      "description": "Bottle temperature",
      "units": "degC",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "c14_dark": {
      "description": "14C assimilation dark/control bottle",
      "units": "mgC/m3/hld",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "c14_mean": {
      "description": "Mean 14C assimilation of replicates 1 and 2",
      "units": "mgC/m3/hld",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "c14_rep1": {
      "description": "14C assimilation replicate 1",
      "units": "mgC/m3/hld",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "c14_rep2": {
      "description": "14C assimilation replicate 2",
      "units": "mgC/m3/hld",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "calf_count": {
      "description": "Number of calves in a sighted cetacean group (obs_attribute)",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "call_type": {
      "description": "Marine mammal call type heard in an hour of sonobuoy recording (obs_attribute; e.g. blue whale B call, fin whale 20 Hz song)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "sio_cetacean-sonobuoy"
      ]
    },
    "carapace_length": {
      "description": "Carapace length of an individual crab larva (rostrum tip to posterior margin of carapace)",
      "units": "mm",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 100,
      "datasets": [
        "cdfw_dungeness-crab"
      ]
    },
    "chl_fluor": {
      "description": "Fluorescence (calibrated)",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": -1,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_mets"
      ]
    },
    "chl_integrated": {
      "description": "Chlorophyll-a integrated over the top 200 m (or the cast bottom): the sum of the 1 m bins",
      "units": "mg/m2",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 200000,
      "derivation": "calcofi4db::ctd_integrate(z_max = 200, z_top_max = 5, method = 'sum'): the sum of the 1 m bins of est_chlorophyll_a_sta_corr (ug/L = mg/m3) from the surface to 200 m or the deepest good bin; the provider's CTD rule (Rasmus Swalethorp 2026-09-23, questions Q02); a bin missing inside the profile is interpolated, the shallowest bin is carried to the surface when it is no deeper than 5 m, else absent; chl_integrated_depth says how deep it reached",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "chl_integrated_depth": {
      "description": "Depth reached by chl_integrated (200 m unless the cast is shallower)",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 200,
      "derivation": "calcofi4db::ctd_integrate(): min(200, deepest good bin) (questions Q02)",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "chl_max": {
      "description": "Chlorophyll-a at its maximum: the 3 m running mean at chl_max_depth",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 1000,
      "derivation": "calcofi4db::ctd_chl_max(window_m = 3): the 3 m running mean of est_chlorophyll_a_sta_corr at chl_max_depth (questions Q02)",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "chl_max_depth": {
      "description": "Depth of the chlorophyll-a maximum (DCM): the highest value of a 3 m running mean",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 200,
      "derivation": "calcofi4db::ctd_chl_max(window_m = 3) on est_chlorophyll_a_sta_corr: the depth of the highest value of a 3 m running mean (each 1 m bin with its neighbours, truncated at the ends of the profile); the provider's definition (Rasmus Swalethorp 2026-09-23, questions Q02)",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "chlorophyll_a": {
      "description": "Chlorophyll-a measured fluorometrically",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": -1,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "cloud_amount": {
      "description": "Cloud amount in oktas (WMO 2700)",
      "units": "oktas",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "cloud_type": {
      "description": "WMO cloud type code (WMO 0500)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "count": {
      "description": "Organism count per survey transect",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "farallon_bird-mammal"
      ]
    },
    "ctdtemp_its90": {
      "description": "CTD temperature (ITS-90 scale)",
      "units": "degC",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_dic"
      ]
    },
    "dic": {
      "description": "Dissolved inorganic carbon",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 5000,
      "datasets": [
        "calcofi_dic"
      ]
    },
    "dic_pco2_raw": {
      "description": "Underway DIC raw pCO2",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "dic_ph_raw": {
      "description": "Underway DIC raw pH",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "dic_rep1": {
      "description": "Dissolved inorganic carbon replicate 1",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 5000,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "dic_rep2": {
      "description": "Dissolved inorganic carbon replicate 2",
      "units": "umol/kg",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "dic_salinity_psu": {
      "description": "Underway DIC system salinity",
      "units": "PSU",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "dic_temp_c": {
      "description": "Underway DIC system temperature",
      "units": "deg_C",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "dic_valve": {
      "description": "Underway DIC valve state",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "dissolved_iron": {
      "description": "Dissolved iron (Fe) concentration",
      "units": "nmol/L",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_iron"
      ]
    },
    "dna_concentration": {
      "description": "Concentration of total DNA after extraction from an eDNA filter",
      "units": "ng/uL",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "dry_air_temp": {
      "description": "Dry air temperature from sling psychrometer",
      "units": "degC",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "dynamic_height": {
      "description": "Dynamic height",
      "units": "dyn m",
      "is_canonical": true,
      "valid_min": -50,
      "valid_max": 50,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "edna_asvs_12s": {
      "description": "Distinct amplicon sequence variants (ASVs) assigned to taxa by the 12S rRNA MiFish assay, per sample, over its PCR replicate libraries",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Count of distinct DNA_sequence values (dnaderiveddata.txt) over the sample’s 12S rRNA MiFish libraries. The provider’s otu_num_tax_assigned (eMoF, archive v1.3) is per library, and PCR replicates share ASVs, so it is not summed; a sample with one library of the assay carries exactly the provider’s value (asserted in the ingest).",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_asvs_dloop": {
      "description": "Distinct amplicon sequence variants (ASVs) assigned to taxa by the mitochondrial D-loop assay, per sample, over its PCR replicate libraries",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Count of distinct DNA_sequence values (dnaderiveddata.txt) over the sample’s mitochondrial D-loop libraries. The provider’s otu_num_tax_assigned (eMoF, archive v1.3) is per library, and PCR replicates share ASVs, so it is not summed; a sample with one library of the assay carries exactly the provider’s value (asserted in the ingest).",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_presence": {
      "description": "Detection (1) or non-detection (0) of the taxon in a sequenced seawater eDNA sample; 0 is not a confirmed absence, and a sample that failed PCR publishes no value (headline occurrence). For calcofi_2022-edna only detections (1) are emitted, so the absence of a row is not a non-detection there; sio_cetacean-edna emits 0 for a sequenced sample with no detection",
      "units": "dimensionless",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 1,
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_12s": {
      "description": "DNA sequence reads assigned to the taxon by the 12S rRNA MiFish metabarcoding assay (fish), per sample; semi-quantitative, not abundance",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum of organismQuantity (organismQuantityType 'DNA sequence reads') over every occurrence of the taxon in the sample's 12S rRNA MiFish libraries: each ASV (distinct sequence) and each PCR replicate library is summed. A semi-quantitative signal of PCR-amplified DNA, NOT abundance: it depends on primer affinity, library depth and the number of replicate libraries, so compare it only within one assay and as a share of edna_reads_filtered_12s for the same sample. Reads from different assays are not comparable and must never be summed.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_dloop": {
      "description": "DNA sequence reads assigned to the taxon by the mitochondrial D-loop metabarcoding assay (cetaceans), per sample; semi-quantitative, not abundance",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum of organismQuantity (organismQuantityType 'DNA sequence reads') over every occurrence of the taxon in the sample's mitochondrial D-loop libraries: each ASV (distinct sequence) and each PCR replicate library is summed. A semi-quantitative signal of PCR-amplified DNA, NOT abundance: it depends on primer affinity, library depth and the number of replicate libraries, so compare it only within one assay and as a share of edna_reads_filtered_dloop for the same sample. Reads from different assays are not comparable and must never be summed.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_filtered_12s": {
      "description": "Sequence reads retained after bioinformatic filtering by the 12S MiFish assay, per sample (normaliser for edna_reads_12s)",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum over the sample's 12S MiFish libraries of the provider's number of sequence reads that passed bioinformatic filtering and were used for the final analyses; the denominator of edna_reads_12s. A library with no published detection is absent from the source archive, so its reads are missing from this total.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_filtered_dloop": {
      "description": "Sequence reads retained after bioinformatic filtering by the D-loop assay, per sample (normaliser for edna_reads_dloop)",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum over the sample's D-loop libraries of the provider's number of sequence reads that passed bioinformatic filtering and were used for the final analyses; the denominator of edna_reads_dloop. A library with no published detection is absent from the source archive, so its reads are missing from this total.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_raw_12s": {
      "description": "Raw sequence reads produced by the 12S MiFish assay before bioinformatic filtering, per sample",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum over the sample's 12S MiFish libraries of the provider's total number of raw sequence reads, before bioinformatic filtering; with edna_reads_filtered_* it gives the share of reads that passed filtering. A library with no published detection is absent from the source archive, so its reads are missing from this total.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "edna_reads_raw_dloop": {
      "description": "Raw sequence reads produced by the D-loop assay before bioinformatic filtering, per sample",
      "units": "reads",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Sum over the sample's D-loop libraries of the provider's total number of raw sequence reads, before bioinformatic filtering; with edna_reads_filtered_* it gives the share of reads that passed filtering. A library with no published detection is absent from the source archive, so its reads are missing from this total.",
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "effort_status": {
      "description": "Whether a cetacean sighting was made on effort and on transect (bin_label ON, bin_value 1) or not (OFF, 0), the analyst-adjusted flag (obs_attribute). A sampling regime, not a quality flag: line-transect density uses ON only.",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "egg_concentration": {
      "description": "Fish or squid eggs per cubic metre of water pumped by the Continuous Underway Fish Egg Sampler (CUFES): the sample's egg count standardized by its minutes sampled and its mean pump speed",
      "units": "count/m3",
      "is_canonical": true,
      "valid_min": 0,
      "derivation": "Ed Weber (SWFSC), 2026-09-25, swfsc_cufes questions Q01: \"The standardization is usually: eggs / m^3 = (count / minutes sampled) / mean pump speed, i.e., eggs / m^3 = (count / (stop time - start time) / ((start pump speed + stop pump speed) / 2)\". Computed in ingest_swfsc_cufes.qmd from Cufes.csv: Stop - Start in minutes, the mean of StartPumpSpeed and StopPumpSpeed (m3/min, Q02); only where the minutes and both pump speeds are present and positive.",
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "est_chlorophyll_a_cruise_corr": {
      "description": "Est. chlorophyll-a cruise-corrected",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 1000,
      "valid_depth_min_m": 0,
      "valid_depth_max_m": 200,
      "derivation": "Fluorometer voltage converted to chlorophyll-a by regression against bottle chlorophyll-a, applied to the 1 m bin-averaged voltage over 0-200 m ONLY - undefined deeper by construction, not by absence of data. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "est_chlorophyll_a_sta_corr": {
      "description": "Est. chlorophyll-a station-corrected",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 1000,
      "valid_depth_min_m": 0,
      "valid_depth_max_m": 200,
      "derivation": "Fluorometer voltage converted to chlorophyll-a by regression against bottle chlorophyll-a, applied to the 1 m bin-averaged voltage over 0-200 m ONLY - undefined deeper by construction, not by absence of data. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "est_nitrate_cruise_corr": {
      "description": "Est. nitrate cruise-corrected",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 200,
      "derivation": "ISUS nitrate sensor voltage converted to nitrate by regression against bottle nitrate. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "est_nitrate_sta_corr": {
      "description": "Est. nitrate station-corrected",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 200,
      "derivation": "ISUS nitrate sensor voltage converted to nitrate by regression against bottle nitrate. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "euphausiid_abundance": {
      "description": "Euphausiid (krill) abundance per net tow, by species and life stage; vertically integrated individuals beneath 1 m2 of sea surface (EDI knb-lter-cce.313.1).",
      "units": "numberPerMeterSquared",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_euphausiids"
      ]
    },
    "fluorescence_v": {
      "description": "Fluorescence voltage",
      "units": "V",
      "is_canonical": true,
      "valid_min": -1,
      "valid_max": 15,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "group_size": {
      "description": "Best estimate of the number of individuals in a sighted cetacean group, visual line-transect survey (headline occurrence per sighting)",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "group_size_max": {
      "description": "Observers' maximum estimate of group size for a cetacean sighting (obs_attribute)",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "group_size_min": {
      "description": "Observers' minimum estimate of group size for a cetacean sighting (obs_attribute)",
      "units": "count",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "hake_eggs": {
      "description": "Pacific hake egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "het_bacteria": {
      "description": "Heterotrophic bacteria abundance (FCM)",
      "units": "number/ml",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_picoplankton-bacteria"
      ]
    },
    "isus_v": {
      "description": "ISUS nitrate voltage",
      "units": "V",
      "is_canonical": true,
      "valid_min": -1,
      "valid_max": 10,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "jack_mackerel_eggs": {
      "description": "Jack mackerel egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "light_pct": {
      "description": "Light intensity of incubation tubes",
      "units": "%",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 100,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "long_wave_rad": {
      "description": "Longwave radiation",
      "units": "W/m2",
      "is_canonical": true,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "mld_sigma_theta_002": {
      "description": "Mixed-layer depth: where sigma-theta is 0.02 kg/m3 greater than at 10 m (CalCOFI legacy definition)",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 6500,
      "derivation": "calcofi4db::ctd_mld(criterion = 'sigma_theta', threshold = 0.02, ref_depth = 10) on the 1 m bins, interpolated linearly between the bracketing bins; the provider's definition (Rasmus Swalethorp 2026-09-23, questions Q01): 'the depth at which sigma-theta is 0.02 kg/m3 greater [than at] a reference depth of 10 m'; absent where the cast never crosses or does not reach 10 m",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "mld_sigma_theta_003": {
      "description": "RETIRED: mixed-layer depth, sigma-theta increase of 0.03 kg/m3 from 10 m (de Boyer Montegut et al. 2004)",
      "units": "m",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 6500,
      "derivation": "RETIRED after v2026.10.01, no longer emitted: the interim headline MLD, superseded by mld_sigma_theta_002, the provider's definition (questions Q01). Was calcofi4db::ctd_mld(criterion = 'sigma_theta', threshold = 0.03, ref_depth = 10); still reproducible with that call",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "mld_sigma_theta_0125": {
      "description": "Mixed-layer depth, sigma-theta increase of 0.125 kg/m3 from 10 m (Levitus 1982)",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 6500,
      "derivation": "calcofi4db::ctd_mld(criterion = 'sigma_theta', threshold = 0.125, ref_depth = 10) on the 1 m bins; an alternative criterion published beside the headline mld_sigma_theta_002 (questions Q01)",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "mld_temperature_02": {
      "description": "Mixed-layer depth, temperature departure of 0.2 degC from 10 m (de Boyer Montegut et al. 2004)",
      "units": "m",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 6500,
      "derivation": "calcofi4db::ctd_mld(criterion = 'temperature', threshold = 0.2, ref_depth = 10) on the 1 m bins; needs no salinity, so the only MLD on preliminary_without_bottle casts; an alternative to the headline mld_sigma_theta_002 (questions Q01)",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "nitrate": {
      "description": "Nitrate concentration",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": -1,
      "valid_max": 60,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_bottle"
      ]
    },
    "nitrite": {
      "description": "Nitrite concentration",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_bottle"
      ]
    },
    "other_fish_eggs": {
      "description": "Other fish egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "oxygen": {
      "description": "Dissolved oxygen",
      "units": null,
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 20,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "oxygen_btl_ml_l": {
      "description": "Bottle dissolved oxygen",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_btl_umol_kg": {
      "description": "Bottle dissolved oxygen",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 700,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_mg_l": {
      "description": "Dissolved oxygen in mg/L (the unit an eDNA filter's co-collected chemistry reports; see oxygen_btl_ml_l / oxygen_umol_kg for the other oxygen units)",
      "units": "mg/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 20,
      "datasets": [
        "calcofi_2022-edna"
      ]
    },
    "oxygen_ml_l": {
      "description": "Dissolved oxygen (QC'd)",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": -0.5,
      "valid_max": 15,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "oxygen_ml_l_1": {
      "description": "DO sensor 1 (uncorrected)",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_1_cruise_corr": {
      "description": "DO sensor 1 cruise-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_1_sta_corr": {
      "description": "DO sensor 1 station-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_2": {
      "description": "DO sensor 2 (uncorrected)",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_2_cruise_corr": {
      "description": "DO sensor 2 cruise-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_2_sta_corr": {
      "description": "DO sensor 2 station-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_ave_cruise_corr": {
      "description": "DO average cruise-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Built by the ingest from the two cruise-corrected oxygen sensors (Ox1_CruiseCorr, Ox2_CruiseCorr) by the sensor-pair flag rule (calcofi4db::combine_sensor_pair_sql(): drop 8/9, honour 1/2, else the mean, one alone when the other is missing). Cruise-corrected = ONE regression per cruise against all its bottles; the source ships no average of this pair.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_ml_l_ave_sta_corr": {
      "description": "DO average station-corrected",
      "units": "ml/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 15,
      "derivation": "Mean of the two station-corrected oxygen sensors. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_sat_pct": {
      "description": "Dissolved oxygen saturation",
      "units": "percent",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 200,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "oxygen_saturation": {
      "description": "Oxygen percent saturation",
      "units": "%",
      "is_canonical": true,
      "valid_min": -1,
      "valid_max": 250,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "oxygen_saturation_1": {
      "description": "Oxygen saturation sensor 1",
      "units": "%",
      "is_canonical": false,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_saturation_2": {
      "description": "Oxygen saturation sensor 2",
      "units": "%",
      "is_canonical": false,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_temp_c": {
      "description": "Oxygen sensor temperature",
      "units": "deg_C",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "oxygen_umol_kg": {
      "description": "Dissolved oxygen (QC'd)",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": -20,
      "valid_max": 700,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "oxygen_umol_kg_1": {
      "description": "DO sensor 1 (uncorrected)",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 700,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_1_cruise_corr": {
      "description": "DO sensor 1 cruise-corrected",
      "units": "umol/kg",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 700,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_1_sta_corr": {
      "description": "DO sensor 1 station-corrected",
      "units": "umol/kg",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 700,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_2": {
      "description": "DO sensor 2 (uncorrected)",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 700,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_2_cruise_corr": {
      "description": "DO sensor 2 cruise-corrected",
      "units": "umol/kg",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 700,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with ONE regression per cruise, fitted from 4-second-averaged sensor data against all the cruise's bottles (n ~ 1400, fliers omitted).",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_2_sta_corr": {
      "description": "DO sensor 2 station-corrected",
      "units": "umol/kg",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 700,
      "derivation": "Sensor oxygen corrected by regression against the bottle oxygens. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "oxygen_umol_kg_ave_sta_corr": {
      "description": "DO average station-corrected",
      "units": "umol/kg",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 700,
      "derivation": "Mean of the two station-corrected oxygen sensors. Bottle-corrected with a regression fitted PER CAST, from 1 m bin-averaged sensor data against that cast's bottles (n ~ 20, fliers omitted). The providers state station-corrected data are the best. Requires a 500 m cast with roughly ten or more bottles, so a null here is by design on shallow or bottle-poor casts.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "par": {
      "description": "Photosynthetically active radiation",
      "units": "uE/m2/s",
      "is_canonical": true,
      "valid_min": -100,
      "valid_max": 5000,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "par_surf": {
      "description": "Surface photosynthetically active radiation",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "ph": {
      "description": "pH",
      "units": "pH",
      "is_canonical": true,
      "valid_min": 6,
      "valid_max": 9,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "ph_rep1": {
      "description": "pH replicate 1",
      "units": "pH",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "ph_rep2": {
      "description": "pH replicate 2",
      "units": "pH",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "phaeopigment": {
      "description": "Phaeopigment measured fluorometrically",
      "units": "ug/L",
      "is_canonical": true,
      "valid_min": -5,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "phosphate": {
      "description": "Phosphate concentration",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_bottle"
      ]
    },
    "phyllosoma_stage_1": {
      "description": "Phyllosoma stage 1 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_10": {
      "description": "Phyllosoma stage 10 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_11": {
      "description": "Phyllosoma stage 11 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_2": {
      "description": "Phyllosoma stage 2 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_3": {
      "description": "Phyllosoma stage 3 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_4": {
      "description": "Phyllosoma stage 4 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_5": {
      "description": "Phyllosoma stage 5 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_6": {
      "description": "Phyllosoma stage 6 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_7": {
      "description": "Phyllosoma stage 7 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_8": {
      "description": "Phyllosoma stage 8 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phyllosoma_stage_9": {
      "description": "Phyllosoma stage 9 count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "phytoplankton_abundance": {
      "description": "Phytoplankton abundance by inverted-microscope count (cells/L)",
      "units": "cells/L",
      "is_canonical": false,
      "datasets": [
        "calcofi_phytoplankton"
      ]
    },
    "picoeukaryotes": {
      "description": "Picoeukaryote abundance (FCM)",
      "units": "number/ml",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_picoplankton-bacteria"
      ]
    },
    "picoplankton_abundance": {
      "description": "Picoplankton and bacteria cell abundance by flow cytometry (FCM); the population counted is obs.taxon_key",
      "units": "number/ml",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_picoplankton-bacteria"
      ]
    },
    "potential_temperature_1": {
      "description": "Potential temperature sensor 1",
      "units": "degC",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "potential_temperature_2": {
      "description": "Potential temperature sensor 2",
      "units": "degC",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "pred_chl": {
      "description": "Estimated chlorophyll-a",
      "units": "ug/L",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "pred_sal_psu": {
      "description": "Model-predicted salinity",
      "units": null,
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "pred_sst_c": {
      "description": "Model-predicted sea-surface temperature (distinct from Pred_TSGTemp)",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "pred_temp_c": {
      "description": "Model-predicted temperature",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "pressure": {
      "description": "Pressure",
      "units": "dbar",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 6500,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "prochlorococcus": {
      "description": "Prochlorococcus abundance (FCM); ~80% populated, see Q01",
      "units": "number/ml",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_picoplankton-bacteria"
      ]
    },
    "prop_sorted": {
      "description": "Fraction of the sample sorted (event-level effort)",
      "units": "dimensionless",
      "is_canonical": true,
      "datasets": [
        "cdfw_dungeness-crab",
        "swfsc_ichthyo"
      ]
    },
    "r_ammonium": {
      "description": "Reported ammonium concentration (pre-QC)",
      "units": "umol/L",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 100,
      "derivation": "reported value interpolated to standard depth (pre-QC, decodr); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "r_depth": {
      "description": "Reported depth from pressure (pre-QC)",
      "units": "m",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 11000,
      "derivation": "reported value interpolated to standard depth (pre-QC, decodr); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "r_dynamic_height": {
      "description": "Reported dynamic height, legacy DECODR value (no QC'd counterpart)",
      "units": "dyn m",
      "is_canonical": false,
      "valid_min": -10,
      "valid_max": 10,
      "derivation": "reported value interpolated to standard depth (pre-QC); computed by DECODR (the bottle database's legacy algorithm), which does not reproduce a Sea-Bird computation (Ben Gire, 2026-10-16), and kept as published (Rasmus Swalethorp, 2026-10-16: keep legacy, add modern, document); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "r_oxygen_umol_kg": {
      "description": "Reported oxygen (pre-QC)",
      "units": "umol/kg",
      "is_canonical": false,
      "derivation": "reported value interpolated to standard depth (pre-QC, decodr); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "r_salinity_sva": {
      "description": "Reported Specific Volume Anomaly (pre-QC); WARNING: different parameter/scale than salinity PSS-78",
      "units": "10^-8 m3/kg",
      "is_canonical": false,
      "derivation": "reported value interpolated to standard depth (pre-QC, decodr); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "r_temperature": {
      "description": "Reported potential temperature (pre-QC)",
      "units": "degC",
      "is_canonical": false,
      "derivation": "reported value interpolated to standard depth (pre-QC, decodr); carries no quality code by design; not an input for further interpolation",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "rel_humidity_pct": {
      "description": "Relative humidity",
      "units": "percent",
      "is_canonical": true,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "salinity": {
      "description": "Salinity - Practical Salinity Scale 1978 (QC'd)",
      "units": "PSS-78",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "salinity_1": {
      "description": "Salinity sensor 1 (uncorrected)",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_1_corr": {
      "description": "Salinity sensor 1 cruise-corrected",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "derivation": "Sensor salinity offset-corrected from bottle salinities BELOW 350 m and applied at all depths, separately for the primary and secondary sensors - a different scheme from the oxygen/nitrate/chlorophyll regressions.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_2": {
      "description": "Salinity sensor 2 (uncorrected)",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_2_corr": {
      "description": "Salinity sensor 2 cruise-corrected",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "derivation": "Sensor salinity offset-corrected from bottle salinities BELOW 350 m and applied at all depths, separately for the primary and secondary sensors - a different scheme from the oxygen/nitrate/chlorophyll regressions.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_ave_corr": {
      "description": "Average salinity corrected",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "derivation": "Mean of the two corrected salinity sensors, each offset-corrected from bottle salinities below 350 m and applied at all depths.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_btl": {
      "description": "Bottle salinity",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "salinity_pss78": {
      "description": "Practical salinity (PSS-78)",
      "units": "PSS-78",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_dic"
      ]
    },
    "sardine_eggs": {
      "description": "Sardine egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "secchi_depth": {
      "description": "Secchi disk depth",
      "units": "meters",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "settled_volume_ml": {
      "description": "Settled volume of the preserved plankton sample (event-level context)",
      "units": "ml",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 10000,
      "datasets": [
        "cdfw_dungeness-crab"
      ]
    },
    "short_wave_rad": {
      "description": "Shortwave radiation",
      "units": "W/m2",
      "is_canonical": true,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "sigma_theta": {
      "description": "Potential density (Sigma Theta), legacy DECODR value",
      "units": "kg/m3",
      "is_canonical": true,
      "valid_min": 15,
      "valid_max": 35,
      "derivation": "computed by DECODR (the bottle database's legacy algorithm) and published as STheta; it does not reproduce a Sea-Bird / TEOS-10 computation from the same temperature and salinity (Ben Gire, 2026-10-16), and is kept as published (Rasmus Swalethorp, 2026-10-16: keep legacy, add modern, document); a TEOS-10 recomputation is planned as a separate dataset",
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "sigma_theta_1": {
      "description": "Potential density sensor 1",
      "units": "kg/m3",
      "is_canonical": true,
      "valid_min": 15,
      "valid_max": 35,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "sigma_theta_2": {
      "description": "Potential density sensor 2",
      "units": "kg/m3",
      "is_canonical": false,
      "valid_min": 15,
      "valid_max": 35,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "sigma_theta_ave": {
      "description": "Potential density anomaly (sigma-theta), sensor-pair average by the provider's flags",
      "units": "kg/m3",
      "is_canonical": true,
      "valid_min": 15,
      "valid_max": 35,
      "derivation": "calcofi4db::ctd_sigma_theta_ave() = combine_sensor_pair() on sigma_theta_1/2: an 8/9-flagged sensor dropped, 1/2 select a sensor, else the mean; final and preliminary_with_bottle casts only",
      "datasets": [
        "calcofi_ctd-derived"
      ]
    },
    "sigma_theta_teos10": {
      "description": "Potential density anomaly (sigma-theta, TEOS-10) per bottle, from the bottle's own temperature and salinity",
      "units": "kg/m3",
      "is_canonical": true,
      "valid_min": -8,
      "valid_max": 37,
      "derivation": "calcofi4db::bottle_spice_sigma0(): sea pressure gsw_p_from_z(-depth, latitude), then gsw_SA_from_SP, gsw_CT_from_t, gsw_sigma0 (TEOS-10, IOC/SCOR/IAPSO 2010) on the bottle's own temperature (T_degC) and salinity (Salnty); a bottle whose T_qual or S_qual is 8 or 9 has none. The bottle database's own sigma_theta is DECODR's legacy value, kept beside it",
      "datasets": [
        "calcofi_bottle-derived"
      ]
    },
    "silicate": {
      "description": "Silicate concentration",
      "units": "umol/L",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 300,
      "datasets": [
        "calcofi_2022-edna",
        "calcofi_bottle"
      ]
    },
    "small_plankton_biomass": {
      "description": "Small plankton displacement-volume biomass (event-level)",
      "units": "mL",
      "is_canonical": true,
      "datasets": [
        "swfsc_ichthyo"
      ]
    },
    "spar": {
      "description": "Surface PAR",
      "units": "uE/m2/s",
      "is_canonical": true,
      "valid_min": -100,
      "valid_max": 5000,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "specific_volume_anomaly": {
      "description": "Specific volume anomaly",
      "units": "10^-8 m3/kg",
      "is_canonical": true,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "spiciness0": {
      "description": "Spice (spiciness at 0 dbar, TEOS-10); positive spicy (warm, salty), negative minty",
      "units": "kg/m3",
      "is_canonical": true,
      "valid_min": -25,
      "valid_max": 18,
      "derivation": "calcofi4db::ctd_spice(): gsw_SA_from_SP, gsw_CT_from_t, gsw_spiciness0 (McDougall & Krzysik 2015). calcofi_ctd-derived: on the sensor-pair averaged corrected temperature and salinity of each 1 m bin, final and preliminary_with_bottle casts only. calcofi_bottle-derived: calcofi4db::bottle_spice_sigma0() on each bottle's own temperature and salinity at gsw_p_from_z(-depth, latitude); a bottle with T_qual or S_qual 8/9 has none",
      "datasets": [
        "calcofi_bottle-derived",
        "calcofi_ctd-derived"
      ]
    },
    "squid_eggs": {
      "description": "Squid egg count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "swfsc_cufes"
      ]
    },
    "ss_conductivity": {
      "description": "Sea surface conductivity (independent sensor)",
      "units": "S/m",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "sss_psu": {
      "description": "Sea surface salinity (raw)",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "sss_psu_corrected": {
      "description": "Corrected sea surface salinity",
      "units": "PSU",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "sst_c": {
      "description": "Sea surface temperature (raw)",
      "units": "deg_C",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "sst_c_corrected": {
      "description": "Corrected sea surface temperature",
      "units": "deg_C",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "stage": {
      "description": "Egg or larva developmental stage (obs_freq binned attribute; labeled via lookup)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "calcofi_phyllosoma",
        "swfsc_ichthyo"
      ]
    },
    "std_haul_factor": {
      "description": "Standardized haul factor (Smith & Richardson 1977; event-level effort)",
      "units": "dimensionless",
      "is_canonical": true,
      "datasets": [
        "swfsc_ichthyo"
      ]
    },
    "sw_ph": {
      "description": "Seawater pH",
      "units": null,
      "is_canonical": true,
      "valid_min": 6,
      "valid_max": 9,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "synechococcus": {
      "description": "Synechococcus abundance (FCM)",
      "units": "number/ml",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_picoplankton-bacteria"
      ]
    },
    "temperature": {
      "description": "Water temperature (QC'd)",
      "units": "degC",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "temperature_1": {
      "description": "Temperature sensor 1",
      "units": "degC",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "temperature_2": {
      "description": "Temperature sensor 2",
      "units": "degC",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "temperature_ave": {
      "description": "Average temperature",
      "units": "degC",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "derivation": "Mean of the two temperature sensors.",
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "total_phyllosoma": {
      "description": "Total phyllosoma larvae count",
      "units": "count",
      "is_canonical": false,
      "datasets": [
        "calcofi_phyllosoma"
      ]
    },
    "total_plankton_biomass": {
      "description": "Total plankton displacement-volume biomass (event-level)",
      "units": "mL",
      "is_canonical": true,
      "datasets": [
        "swfsc_ichthyo"
      ]
    },
    "transect_length": {
      "description": "Length of an on-effort, on-transect visual survey segment (event-level effort)",
      "units": "km",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "sio_cetacean-sightings"
      ]
    },
    "transmissometer": {
      "description": "Light transmissometer",
      "units": "%",
      "is_canonical": true,
      "datasets": [
        "calcofi_ctd-cast"
      ]
    },
    "transmissometer_v": {
      "description": "Transmissometer voltage",
      "units": "V",
      "is_canonical": false,
      "valid_min": -1,
      "valid_max": 15,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_conductivity": {
      "description": "TSG unit 1 conductivity",
      "units": "S/m",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_density": {
      "description": "TSG unit 1 density",
      "units": "kg/m3",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_salinity_psu": {
      "description": "TSG unit 1 salinity",
      "units": "PSU",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_salinity_psu_calibrated": {
      "description": "Calibrated salinity",
      "units": "PSU",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_sound_velocity": {
      "description": "TSG unit 1 sound velocity",
      "units": "m/s",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_temp_c": {
      "description": "TSG unit 1 temperature (physical sensor unconfirmed -- mets_03)",
      "units": "deg_C",
      "is_canonical": true,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg1_temp_c_calibrated": {
      "description": "Calibrated temperature",
      "units": "deg_C",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2_conductivity": {
      "description": "TSG unit 2 conductivity",
      "units": "S/m",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 10,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2_density": {
      "description": "TSG unit 2 density",
      "units": "kg/m3",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2_salinity_psu": {
      "description": "TSG unit 2 salinity",
      "units": "PSU",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2_sound_velocity": {
      "description": "TSG unit 2 sound velocity",
      "units": "m/s",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2_temp_c": {
      "description": "TSG unit 2 temperature (physical sensor unconfirmed -- mets_03)",
      "units": "deg_C",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg2b_temp_c": {
      "description": "A SECOND unit-2 temperature appearing alongside TSG_Temp_2 in one file",
      "units": "deg_C",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg3_conductivity": {
      "description": "TSG unit 3 conductivity",
      "units": "S/m",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg3_density": {
      "description": "TSG unit 3 density",
      "units": "kg/m3",
      "is_canonical": false,
      "valid_min": 900,
      "valid_max": 1100,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg3_salinity_psu": {
      "description": "TSG unit 3 salinity",
      "units": "PSU",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg3_sound_velocity": {
      "description": "TSG unit 3 sound velocity",
      "units": "m/s",
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg3_temp_c": {
      "description": "TSG unit 3 temperature (physical sensor unconfirmed -- mets_03)",
      "units": "deg_C",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg5_salinity_psu": {
      "description": "TSG unit 5 salinity",
      "units": "PSU",
      "is_canonical": false,
      "valid_min": 0,
      "valid_max": 45,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "tsg5_temp_c": {
      "description": "TSG unit 5 temperature (physical sensor unconfirmed -- mets_03)",
      "units": "deg_C",
      "is_canonical": false,
      "valid_min": -2,
      "valid_max": 40,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "unknown_measurement_1": {
      "description": "Unidentified measurement (NaN in every file inspected)",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "unknown_measurement_2": {
      "description": "Unidentified measurement (NaN in every file inspected)",
      "units": null,
      "is_canonical": false,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "uws_flow": {
      "description": "Underway seawater flow rate",
      "units": "L/min",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "visibility": {
      "description": "WMO visibility code (WMO 4300)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "volume_sampled": {
      "description": "Volume of water filtered by the net (event-level effort)",
      "units": "m3",
      "is_canonical": true,
      "datasets": [
        "swfsc_ichthyo"
      ]
    },
    "water_color": {
      "description": "Water color on Forel-Ule scale",
      "units": "Forel-Ule",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wave_direction": {
      "description": "Wave direction (abbreviated 360 degree azimuth)",
      "units": "degrees",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wave_height": {
      "description": "Wave height",
      "units": "feet",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wave_period": {
      "description": "Wave period",
      "units": "seconds",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "weather_code": {
      "description": "WMO weather code (WMO 4501)",
      "units": null,
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wet_air_temp": {
      "description": "Wet air temperature from sling psychrometer",
      "units": "degC",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wind_dir_deg": {
      "description": "Wind direction",
      "units": "degrees",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 360,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "wind_direction": {
      "description": "Wind direction (abbreviated 360 degree azimuth)",
      "units": "degrees",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wind_speed": {
      "description": "Wind speed",
      "units": "knots",
      "is_canonical": true,
      "datasets": [
        "calcofi_bottle"
      ]
    },
    "wind_speed_ms": {
      "description": "Wind speed",
      "units": "m/s",
      "is_canonical": true,
      "valid_min": 0,
      "valid_max": 120,
      "datasets": [
        "calcofi_mets"
      ]
    },
    "zooplankton_abundance": {
      "description": "Zooplankton numerical abundance (volumetric density) per net tow, by higher taxon. Raw (uncorrected for net type).",
      "units": "count/1000m3",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zoodb"
      ]
    },
    "zooplankton_abundance_areal": {
      "description": "Zooplankton areal abundance (depth-integrated density) per net tow, by higher taxon. Raw (uncorrected).",
      "units": "count/m2",
      "is_canonical": false,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zoodb"
      ]
    },
    "zooplankton_biomass_carbon": {
      "description": "Zooplankton carbon biomass per net tow, by higher taxon. Raw (uncorrected for net type).",
      "units": "mgC/m2",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zoodb"
      ]
    },
    "zooscan_abundance": {
      "description": "Zooplankton areal abundance from ZooScan optical imaging, by image-classified bioclass.",
      "units": "count/m2",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zooscan"
      ]
    },
    "zooscan_biomass_carbon": {
      "description": "Estimated zooplankton carbon biomass from ZooScan optical imaging, by bioclass.",
      "units": "mgC/m2",
      "is_canonical": true,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zooscan"
      ]
    },
    "zooscan_carbon_individual": {
      "description": "Mean individual carbon content from ZooScan optical imaging, by bioclass.",
      "units": "ugC",
      "is_canonical": false,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zooscan"
      ]
    },
    "zooscan_feret_diameter": {
      "description": "Mean Feret diameter (organism size) from ZooScan optical imaging, by bioclass.",
      "units": "mm",
      "is_canonical": false,
      "valid_min": 0,
      "datasets": [
        "cce-lter_zooscan"
      ]
    }
  },
  "contributions": {
    "sample": {
      "total_rows": 1467375,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_bottle",
          "rows": 931015,
          "pct": 63.4,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle.html"
        },
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 212249,
          "pct": 14.5,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        },
        {
          "provider_dataset": "sio_pic-zooplankton",
          "rows": 82343,
          "pct": 5.6,
          "workflow": "https://calcofi.io/workflows/ingest_sio_pic-zooplankton.html"
        },
        {
          "provider_dataset": "calcofi_mets",
          "rows": 77791,
          "pct": 5.3,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_mets.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 64421,
          "pct": 4.4,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        },
        {
          "provider_dataset": "swfsc_cufes",
          "rows": 47989,
          "pct": 3.3,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
        },
        {
          "provider_dataset": "calcofi_ctd-cast",
          "rows": 19704,
          "pct": 1.3,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html"
        },
        {
          "provider_dataset": "cce-lter_picoplankton-bacteria",
          "rows": 16017,
          "pct": 1.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html"
        },
        {
          "provider_dataset": "cce-lter_euphausiids",
          "rows": 7482,
          "pct": 0.5,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html"
        },
        {
          "provider_dataset": "calcofi_dic",
          "rows": 3262,
          "pct": 0.2,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_dic.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 1859,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "cce-lter_zooscan",
          "rows": 1483,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 526,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        },
        {
          "provider_dataset": "cce-lter_zoodb",
          "rows": 506,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html"
        },
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 409,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "cce-lter_iron",
          "rows": 170,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_iron.html"
        },
        {
          "provider_dataset": "sio_mesopelagic-fish",
          "rows": 102,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html"
        },
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 47,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        }
      ]
    },
    "obs": {
      "total_rows": 35358143,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_ctd-cast",
          "rows": 19060086,
          "pct": 53.9,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html"
        },
        {
          "provider_dataset": "calcofi_bottle",
          "rows": 11135581,
          "pct": 31.5,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle.html"
        },
        {
          "provider_dataset": "calcofi_bottle-derived",
          "rows": 1683346,
          "pct": 4.8,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle-derived.html"
        },
        {
          "provider_dataset": "calcofi_ctd-derived",
          "rows": 1364381,
          "pct": 3.9,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html"
        },
        {
          "provider_dataset": "swfsc_cufes",
          "rows": 550162,
          "pct": 1.6,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
        },
        {
          "provider_dataset": "calcofi_mets",
          "rows": 511395,
          "pct": 1.4,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_mets.html"
        },
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 487616,
          "pct": 1.4,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        },
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 155553,
          "pct": 0.4,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "cce-lter_zooscan",
          "rows": 126692,
          "pct": 0.4,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html"
        },
        {
          "provider_dataset": "cce-lter_euphausiids",
          "rows": 100505,
          "pct": 0.3,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 69661,
          "pct": 0.2,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        },
        {
          "provider_dataset": "cce-lter_picoplankton-bacteria",
          "rows": 60802,
          "pct": 0.2,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html"
        },
        {
          "provider_dataset": "cce-lter_zoodb",
          "rows": 30948,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html"
        },
        {
          "provider_dataset": "calcofi_dic",
          "rows": 16389,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_dic.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 1859,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 1456,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        },
        {
          "provider_dataset": "sio_mesopelagic-fish",
          "rows": 1393,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html"
        },
        {
          "provider_dataset": "cce-lter_iron",
          "rows": 170,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_iron.html"
        },
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 148,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        }
      ]
    },
    "sample_measurement": {
      "total_rows": 659307,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 324284,
          "pct": 49.2,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        },
        {
          "provider_dataset": "calcofi_bottle",
          "rows": 268876,
          "pct": 40.8,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle.html"
        },
        {
          "provider_dataset": "calcofi_ctd-derived",
          "rows": 64994,
          "pct": 9.9,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 617,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        },
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 536,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        }
      ]
    },
    "taxon": {
      "total_rows": 2606,
      "over_attributed": true,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 79,
          "pct": 3,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 13,
          "pct": 0.5,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 524,
          "pct": 20.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "cce-lter_euphausiids",
          "rows": 54,
          "pct": 2.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html"
        },
        {
          "provider_dataset": "cce-lter_picoplankton-bacteria",
          "rows": 13,
          "pct": 0.5,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html"
        },
        {
          "provider_dataset": "cce-lter_zoodb",
          "rows": 75,
          "pct": 2.9,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html"
        },
        {
          "provider_dataset": "cce-lter_zooscan",
          "rows": 42,
          "pct": 1.6,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 17,
          "pct": 0.7,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 266,
          "pct": 10.2,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        },
        {
          "provider_dataset": "sio_mesopelagic-fish",
          "rows": 206,
          "pct": 7.9,
          "workflow": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html"
        },
        {
          "provider_dataset": "swfsc_cufes",
          "rows": 34,
          "pct": 1.3,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
        },
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 1686,
          "pct": 64.7,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "dataset_taxon": {
      "total_rows": 1940,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 19,
          "pct": 1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 1,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 393,
          "pct": 20.3,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "cce-lter_euphausiids",
          "rows": 37,
          "pct": 1.9,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html"
        },
        {
          "provider_dataset": "cce-lter_picoplankton-bacteria",
          "rows": 4,
          "pct": 0.2,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html"
        },
        {
          "provider_dataset": "cce-lter_zoodb",
          "rows": 33,
          "pct": 1.7,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html"
        },
        {
          "provider_dataset": "cce-lter_zooscan",
          "rows": 23,
          "pct": 1.2,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 3,
          "pct": 0.2,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 164,
          "pct": 8.5,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        },
        {
          "provider_dataset": "sio_mesopelagic-fish",
          "rows": 90,
          "pct": 4.6,
          "workflow": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html"
        },
        {
          "provider_dataset": "swfsc_cufes",
          "rows": 6,
          "pct": 0.3,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
        },
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 1167,
          "pct": 60.2,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "measurement_type": {
      "total_rows": 234,
      "over_attributed": true,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_2022-edna",
          "rows": 234,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html"
        },
        {
          "provider_dataset": "calcofi_bottle-derived",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle-derived.html"
        },
        {
          "provider_dataset": "calcofi_bottle",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_bottle.html"
        },
        {
          "provider_dataset": "calcofi_ctd-cast",
          "rows": 234,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html"
        },
        {
          "provider_dataset": "calcofi_ctd-derived",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html"
        },
        {
          "provider_dataset": "calcofi_dic",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_dic.html"
        },
        {
          "provider_dataset": "calcofi_mets",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_mets.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "cce-lter_euphausiids",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_euphausiids.html"
        },
        {
          "provider_dataset": "cce-lter_iron",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_iron.html"
        },
        {
          "provider_dataset": "cce-lter_picoplankton-bacteria",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_picoplankton-bacteria.html"
        },
        {
          "provider_dataset": "cce-lter_zoodb",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zoodb.html"
        },
        {
          "provider_dataset": "cce-lter_zooscan",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_cce-lter_zooscan.html"
        },
        {
          "provider_dataset": "sio_mesopelagic-fish",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_sio_mesopelagic-fish.html"
        },
        {
          "provider_dataset": "swfsc_cufes",
          "rows": 232,
          "pct": 99.1,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_cufes.html"
        }
      ]
    },
    "obs_ctd_full": {
      "total_rows": 286148056,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_ctd-cast",
          "rows": 286148056,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_ctd-cast.html"
        }
      ]
    },
    "obs_mets_full": {
      "total_rows": 19926523,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_mets",
          "rows": 19926523,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_mets.html"
        }
      ]
    },
    "obs_attribute": {
      "total_rows": 455300,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 367094,
          "pct": 80.6,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 87813,
          "pct": 19.3,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        },
        {
          "provider_dataset": "calcofi_phyllosoma",
          "rows": 369,
          "pct": 0.1,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phyllosoma.html"
        },
        {
          "provider_dataset": "cdfw_dungeness-crab",
          "rows": 24,
          "pct": 0,
          "workflow": "https://calcofi.io/workflows/ingest_cdfw_dungeness-crab.html"
        }
      ]
    },
    "taxon_group": {
      "total_rows": 438,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 308,
          "pct": 70.3,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        },
        {
          "provider_dataset": "farallon_bird-mammal",
          "rows": 130,
          "pct": 29.7,
          "workflow": "https://calcofi.io/workflows/ingest_farallon_bird-mammal.html"
        }
      ]
    },
    "region": {
      "total_rows": 4,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "calcofi_phytoplankton",
          "rows": 4,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html"
        }
      ]
    },
    "cruise": {
      "total_rows": 869,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 739,
          "pct": 85,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "ship": {
      "total_rows": 49,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 48,
          "pct": 98,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "lookup": {
      "total_rows": 26,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 26,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "grid": {
      "total_rows": 225,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 225,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "fish": {
      "total_rows": 10796,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 10796,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    },
    "ichthyo_net": {
      "total_rows": 77888,
      "over_attributed": false,
      "by_dataset": [
        {
          "provider_dataset": "swfsc_ichthyo",
          "rows": 77888,
          "pct": 100,
          "workflow": "https://calcofi.io/workflows/ingest_swfsc_ichthyo.html"
        }
      ]
    }
  },
  "erd_legend": [
    {
      "provider_dataset": "calcofi_2022-edna",
      "color": "#bbe0f0"
    },
    {
      "provider_dataset": "calcofi_bottle-derived",
      "color": "#d3dcf2"
    },
    {
      "provider_dataset": "calcofi_bottle",
      "color": "#f5cad9"
    },
    {
      "provider_dataset": "calcofi_ctd-cast",
      "color": "#e0ccf0"
    },
    {
      "provider_dataset": "calcofi_ctd-derived",
      "color": "#cfe8dc"
    },
    {
      "provider_dataset": "calcofi_dic",
      "color": "#ffd2bb"
    },
    {
      "provider_dataset": "calcofi_mets",
      "color": "#cce5ff"
    },
    {
      "provider_dataset": "calcofi_phyllosoma",
      "color": "#e0bbf0"
    },
    {
      "provider_dataset": "calcofi_phytoplankton",
      "color": "#b5e8b0"
    },
    {
      "provider_dataset": "cce-lter_euphausiids",
      "color": "#d2f0bb"
    },
    {
      "provider_dataset": "cce-lter_iron",
      "color": "#f0e0c0"
    },
    {
      "provider_dataset": "cce-lter_picoplankton-bacteria",
      "color": "#bbe0f0"
    },
    {
      "provider_dataset": "cce-lter_zoodb",
      "color": "#d9c2f0"
    },
    {
      "provider_dataset": "cce-lter_zooscan",
      "color": "#c2e8f0"
    },
    {
      "provider_dataset": "cdfw_dungeness-crab",
      "color": "#f5d5b8"
    },
    {
      "provider_dataset": "farallon_bird-mammal",
      "color": "#f0d2e8"
    },
    {
      "provider_dataset": "sio_mesopelagic-fish",
      "color": "#bbe0f0"
    },
    {
      "provider_dataset": "sio_pic-zooplankton",
      "color": "#bbe0f0"
    },
    {
      "provider_dataset": "swfsc_cufes",
      "color": "#f0e8bb"
    },
    {
      "provider_dataset": "swfsc_ichthyo",
      "color": "#cdebc6"
    }
  ]
}