{ "schema_version": "1.1", "provider": "calcofi", "dataset": "phytoplankton", "workflow": "https://calcofi.io/workflows/ingest_calcofi_phytoplankton.html", "tables": { "sample": { "name_long": "Sample", "description_md": "One row per physical sampling event at its native grain (site, tow, net, cast, bottle, underway, transect, 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`." }, "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`." }, "taxon": { "name_long": "Taxon", "description_md": "One authoritative row per taxon, keyed by `taxon_key` = `worms:` (or `itis:` for birds). Replaces the per-dataset taxon tables; duplicates across datasets collapse to one row, with names and lineage coalesced by source priority." }, "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." }, "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." }, "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." }, "measurement_type": { "name_long": "Measurement Type", "description_md": "" }, "dataset": { "name_long": "Dataset", "description_md": "" } }, "columns": { "dataset.provider": { "name_long": "Provider", "units": null, "description_md": "" }, "dataset.dataset": { "name_long": "Dataset", "units": null, "description_md": "" }, "dataset.dataset_name": { "name_long": "Dataset Name", "units": null, "description_md": "" }, "dataset.dataset_name_short": { "name_long": "Dataset Name Short", "units": null, "description_md": "" }, "dataset.category": { "name_long": "Category", "units": null, "description_md": "" }, "dataset.color": { "name_long": "Color", "units": null, "description_md": "" }, "dataset.description": { "name_long": "Description", "units": null, "description_md": "" }, "dataset.citation_main": { "name_long": "Citation Main", "units": null, "description_md": "" }, "dataset.citation_others": { "name_long": "Citation Others", "units": null, "description_md": "" }, "dataset.link_calcofi_org": { "name_long": "Link Calcofi Org", "units": null, "description_md": "" }, "dataset.link_data_source": { "name_long": "Link Data Source", "units": null, "description_md": "" }, "dataset.link_others": { "name_long": "Link Others", "units": null, "description_md": "" }, "dataset.tables": { "name_long": "Tables", "units": null, "description_md": "" }, "dataset.coverage_temporal": { "name_long": "Coverage Temporal", "units": null, "description_md": "" }, "dataset.coverage_spatial": { "name_long": "Coverage Spatial", "units": null, "description_md": "" }, "dataset.license": { "name_long": "License", "units": null, "description_md": "" }, "dataset.pi_names": { "name_long": "Pi Names", "units": null, "description_md": "" }, "dataset.doi": { "name_long": "Doi", "units": null, "description_md": "" }, "dataset.license_url": { "name_long": "License Url", "units": null, "description_md": "" }, "dataset.acknowledgement": { "name_long": "Acknowledgement", "units": null, "description_md": "" }, "dataset.contact": { "name_long": "Contact", "units": null, "description_md": "" }, "dataset_taxon.ds_taxon_key": { "name_long": "Dataset Taxon Key", "description_md": "Key of this crosswalk row, `:`." }, "dataset_taxon.dataset_key": { "name_long": "Dataset Key", "description_md": "The dataset whose vocabulary this row belongs to." }, "dataset_taxon.taxon_key": { "name_long": "Taxon Key", "description_md": "The global taxon it resolves to; joins `taxon`." }, "dataset_taxon.ds_scientific_name": { "name_long": "Dataset Scientific Name", "description_md": "Scientific name as the source dataset spells it." }, "dataset_taxon.ds_common_name": { "name_long": "Dataset Common Name", "description_md": "Common name as the source dataset spells it." }, "dataset_taxon.ds_taxa_code": { "name_long": "Dataset Taxa Code", "description_md": "The dataset's own code, as stored on its measurement rows." }, "dataset_taxon.ds_source_json": { "name_long": "Ds Source Json", "units": null, "description_md": "" }, "measurement_type.measurement_type": { "name_long": "Measurement Type", "units": null, "description_md": "" }, "measurement_type.description": { "name_long": "Description", "units": null, "description_md": "" }, "measurement_type.units": { "name_long": "Units", "units": null, "description_md": "" }, "measurement_type.valid_min": { "name_long": "Valid Min", "units": null, "description_md": "" }, "measurement_type.valid_max": { "name_long": "Valid Max", "units": null, "description_md": "" }, "measurement_type.valid_depth_min_m": { "name_long": "Valid Depth Min M", "units": null, "description_md": "" }, "measurement_type.valid_depth_max_m": { "name_long": "Valid Depth Max M", "units": null, "description_md": "" }, "measurement_type.derivation": { "name_long": "Derivation", "units": null, "description_md": "" }, "measurement_type.is_canonical": { "name_long": "Is Canonical", "units": null, "description_md": "" }, "measurement_type._source_column": { "name_long": " Source Column", "units": null, "description_md": "" }, "measurement_type._source_table": { "name_long": " Source Table", "units": null, "description_md": "" }, "measurement_type._source_datasets": { "name_long": " Source Datasets", "units": null, "description_md": "" }, "measurement_type._qual_column": { "name_long": " Qual Column", "units": null, "description_md": "" }, "measurement_type._prec_column": { "name_long": " Prec Column", "units": null, "description_md": "" }, "measurement_type.grain": { "name_long": "Grain", "units": null, "description_md": "" }, "measurement_type.denominator": { "name_long": "Denominator", "units": null, "description_md": "" }, "measurement_type.category": { "name_long": "Category", "units": null, "description_md": "" }, "measurement_type.variable": { "name_long": "Variable", "units": null, "description_md": "" }, "measurement_type.nerc_p01": { "name_long": "Nerc P01", "units": null, "description_md": "" }, "measurement_type.units_nerc_p06": { "name_long": "Units Nerc P06", "units": null, "description_md": "" }, "obs.obs_id": { "name_long": "Observation ID", "description_md": "Surrogate key, renumbered globally when the release concatenates the per-dataset shards." }, "obs.realm": { "name_long": "Realm", "description_md": "`env` for physical/chemical measurements, `bio` for organism observations." }, "obs.dataset_key": { "name_long": "Dataset Key", "description_md": "Provenance stamp: `provider_dataset`." }, "obs.sample_key": { "name_long": "Sample Key", "description_md": "The sampling event this observation came from; joins `sample`." }, "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." }, "obs.cruise_key": { "name_long": "Cruise Key", "description_md": "Cruise, denormalized from `sample` so rollups need no join." }, "obs.latitude": { "name_long": "Latitude", "units": "decimal degrees", "description_md": "Observation latitude (WGS84)." }, "obs.longitude": { "name_long": "Longitude", "units": "decimal degrees", "description_md": "Observation longitude (WGS84)." }, "obs.datetime": { "name_long": "Datetime", "description_md": "Observation time (UTC). NULL for region-pooled data with no event time." }, "obs.depth_min_m": { "name_long": "Depth Min", "units": "m", "description_md": "Shallowest depth this observation represents." }, "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)." }, "obs.taxon_key": { "name_long": "Taxon Key", "description_md": "Global taxon key, `worms:` or `itis:` for birds. NULL for `env` rows. Joins `taxon`." }, "obs.life_stage": { "name_long": "Life Stage", "description_md": "Life stage where the source resolves one (larva, adult, juvenile, egg, phyllosoma)." }, "obs.measurement_type": { "name_long": "Measurement Type", "description_md": "Measured quantity; joins the `measurement_type` vocabulary." }, "obs.measurement_value": { "name_long": "Measurement Value", "description_md": "The measured value, in the units `measurement_type` declares." }, "obs.measurement_qual": { "name_long": "Measurement Qualifier", "description_md": "Source quality flag, verbatim." }, "obs.measurement_prec": { "name_long": "Measurement Precision", "description_md": "Source-reported precision where available." }, "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." }, "region.region_key": { "name_long": "Region", "description_md": "Pooled-region code: NE, SE, Alley, or Offshore (primary key)." }, "region.description": { "name_long": "Description", "description_md": "Region description (Northern Inshore, Southern Inshore, California Current, Central Pacific)." }, "region.latitude": { "name_long": "Latitude", "units": "decimal degrees", "description_md": "Provisional region centroid latitude (mean of member CalCOFI stations; Q01)." }, "region.longitude": { "name_long": "Longitude", "units": "decimal degrees", "description_md": "Provisional region centroid longitude (mean of member CalCOFI stations; Q01)." }, "region.n_stations": { "name_long": "Number of Stations", "description_md": "Count of CalCOFI grid stations defining the region." }, "region.station_codes": { "name_long": "Station Codes", "description_md": "Member CalCOFI line.station codes (Hayward & Venrick 1998)." }, "region.geom": { "name_long": "Geom", "units": null, "description_md": "" }, "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." }, "sample.sample_type": { "name_long": "Sample Type", "description_md": "Event grain: `site`, `tow`, `net`, `cast`, `bottle`, `underway`, `transect` or `region_pool`." }, "sample.parent_sample_key": { "name_long": "Parent Sample Key", "description_md": "The containing event (net → tow → site; bottle → cast). NULL at the top of the chain. Flat adjacency list: attributes are not inherited." }, "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." }, "sample.dataset_key": { "name_long": "Dataset Key", "description_md": "Provenance stamp: `provider_dataset`." }, "sample.grid_key": { "name_long": "Grid Key", "description_md": "CalCOFI station grid cell. NULL where the dataset has no station assignment (region-pooled phytoplankton)." }, "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." }, "sample.cruise_key": { "name_long": "Cruise Key", "description_md": "CalCOFI cruise natural key `YYYY-MM-NODC`." }, "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." }, "sample.latitude": { "name_long": "Latitude", "units": "decimal degrees", "description_md": "Event latitude (WGS84)." }, "sample.longitude": { "name_long": "Longitude", "units": "decimal degrees", "description_md": "Event longitude (WGS84)." }, "sample.datetime": { "name_long": "Datetime", "description_md": "Event start time (UTC)." }, "sample.depth_min_m": { "name_long": "Depth Min", "units": "m", "description_md": "Shallowest depth sampled by this event." }, "sample.depth_max_m": { "name_long": "Depth Max", "units": "m", "description_md": "Deepest depth sampled by this event." }, "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." }, "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." }, "sample.geom": { "name_long": "Geometry", "description_md": "Point geometry minted from `longitude`/`latitude` (OGC:CRS84)." }, "sample.source_uuid": { "name_long": "Source Uuid", "units": null, "description_md": "" }, "taxon.taxon_key": { "name_long": "Taxon Key", "description_md": "Global taxon key: lowercase authority prefix plus id, `worms:127023` or `itis:176754`." }, "taxon.worms_id": { "name_long": "WoRMS ID", "description_md": "WoRMS AphiaID." }, "taxon.itis_id": { "name_long": "ITIS ID", "description_md": "ITIS Taxonomic Serial Number." }, "taxon.gbif_id": { "name_long": "GBIF ID", "description_md": "GBIF backbone taxon key." }, "taxon.ncbi_id": { "name_long": "NCBI ID", "description_md": "NCBI Taxonomy id." }, "taxon.inat_id": { "name_long": "iNaturalist ID", "description_md": "iNaturalist taxon id." }, "taxon.scientific_name": { "name_long": "Scientific Name", "description_md": "Accepted scientific name." }, "taxon.common_name": { "name_long": "Common Name", "description_md": "Common name where one is recorded." }, "taxon.rank": { "name_long": "Rank", "description_md": "Taxonomic rank." }, "taxon.rank_order": { "name_long": "Rank Order", "description_md": "Ordinal for sorting ranks from kingdom down." }, "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." }, "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." }, "taxon.parent_taxon_key": { "name_long": "Parent Taxon Key", "description_md": "Lineage parent; walk this to expand a taxon to its descendants." }, "taxon.kingdom": { "name_long": "Kingdom", "description_md": "Kingdom." }, "taxon.phylum": { "name_long": "Phylum", "description_md": "Phylum." }, "taxon.class": { "name_long": "Class", "description_md": "Class." }, "taxon.order_taxon": { "name_long": "Order", "description_md": "Order (named `order_taxon` because `order` is a SQL keyword)." }, "taxon.family": { "name_long": "Family", "description_md": "Family." }, "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`." }, "taxon_group.taxon_group_key": { "name_long": "Taxon Group Key", "description_md": "Group key, `:`." }, "taxon_group.description": { "name_long": "Description", "description_md": "Human-readable description of the group." }, "taxon_group.taxon_key": { "name_long": "Taxon Key", "description_md": "A member taxon; joins `taxon`." } }, "contributions": { "sample": { "rows": 409, "owned": true, "shared": true }, "obs": { "rows": 159804, "owned": true, "shared": true }, "taxon": { "rows": 542, "owned": true, "shared": true }, "dataset_taxon": { "rows": 393, "owned": true, "shared": true }, "taxon_group": { "rows": 311, "owned": true, "shared": true }, "region": { "rows": 4, "owned": true, "shared": false }, "measurement_type": { "rows": 200, "owned": true, "shared": true } } }