CalCOFI integrated database release v2026.10.20

Release date: 2026-10-20 · promoted (latest.txt)

SWFSC's 14 October export: squid eggs are Abraliopsis felis, FROSTI's cruises key by 18DN, and each net carries its side and tow number

Ed Weber's 2026-10-14 export of the SWFSC CalCOFI database answers the ten questions of 2026-10-06 (metadata/swfsc/ichthyo/questions.csv Q14, Q17–Q25; metadata/swfsc/cufes/questions.csv Q09–Q15). swfsc_ichthyo and swfsc_cufes are re-ingested from it; no column was added or removed in any of its 17 tables. The sections below are what a consumer sees change.

CUFES "squid eggs" are Abraliopsis felis, not market squid

"Bill says we can safely call these Abraliopsis felis, sppcode 9561, AphiaID 341849, because they are the only squid in this region that have pelagic eggs" (Ed Weber, 2026-10-14; swfsc_cufes Q11, the opposite of what we had proposed). metadata/measurement_taxon.csv keys squid_eggs and squid_eggs_per_m3 to Abraliopsis felis (worms:341849, ITIS 82401); through v2026.10.19 they were keyed to Doryteuthis opalescens (worms:574540).

Consumers: every obs_bio row of swfsc_cufes with measurement_type squid_eggs / squid_eggs_per_m3 (82,334 rows: 41,167 counts and 41,167 concentrations, 18,131 of each with eggs) changes taxon_key from worms:574540 to worms:341849; the species face and the Explorer label change from "Market squid" to Abraliopsis felis. A query keyed on worms:574540 finds no CUFES rows in this release.

FROSTI's seven cruises key by NODC 18DN, not OIFS

SWFSC corrected the ship table: "I dug into the NODC codes for Frosti (yes, 18DN) and Bold Horizon today and now have a complete and correct table. Also NODC and ICES codes now correspond completely" (Ed Weber, 2026-10-14; swfsc_ichthyo Q14). create_cruise_key() mints YYYY-MM-NODC from ship.ship_nodc, so the seven FROSTI cruises change key (Ben Best, 2026-10-20, decision D1: adopt the corrected code; NODC's own platform list says 18DN). Every dataset that keys events to them (swfsc_ichthyo, swfsc_cufes, cdfw_dungeness-crab, sio_pic-zooplankton, cce-lter_euphausiids, cce-lter_zoodb; 4,999 sample rows in v2026.10.19) is re-rendered against the new cruise shard, and ship_ices now equals ship_nodc for every ship.

Consumers: the old keys are gone from cruise, sample, obs_bio, obs_env and climatology; map them one to one:

cruise.cruise_uuid is unchanged for all seven, so a join on SWFSC's CruiseId needs no mapping. Measured against v2026.10.19 on the re-ingested shards: 2,750 swfsc_cufes and 2,047 swfsc_ichthyo sample rows change key (one fewer than the 2,048 of v2026.10.19: a removed net-less tow was on 2011-04); the other four datasets re-key at the release run.

One ichthyo species code re-keys: 844 "Microdesmidae" is worms:151793

SWFSC's rebuilt Species table re-points code 844 (Microdesmidae) from AphiaID 151423 (family Microdesmidae) to 151793 (subfamily Microdesminae, WoRMS's accepted placement). The ingest keys what the source supplies, so its 6 obs_bio rows (8 larvae) move from taxon_key worms:151423 to worms:151793; SWFSC's verbatim name stays on dataset_taxon. Every other ichthyo abundance value is identical to v2026.10.19 (487,610 of 487,616 rows pair exactly), and data/flagged/species_worms_lookup_check.csv is empty: every code now keys its own source AphiaID and every SpeciesWormsLookup name agrees with WoRMS (11 rows at v2026.10.19).

Consumers: worms:151423 has no ichthyo rows in this release; read worms:151793.

Each ichthyoplankton net carries its side and tow number: ichthyo_net

The core projection drops two source columns: Net.NetSide (starboard or port of a bongo pair) and Tow.TowNumber (which of several tows of one type at one station occupation). They are what tells the two nets of a CalBOBL or PairoVET tow, and two tows of one type at one occupation, apart, and the SIO Pelagic Invertebrate Collection's "Parent Net Event" table is matched to the released nets on exactly those (Linsey Sala; Ben Best, 2026-10-20, decision D2). New table ichthyo_net, one row per net (77,888): sample_key (the net's; primary key and FK to sample), net_uuid (SWFSC's NetId, = sample.source_uuid), tow_uuid (SWFSC's TowId), net_side (S on 56,248 nets, P on 3,557, NULL on the 18,083 single-net C1, CalVET and Manta nets), tow_number (1 on all but 121 tows; up to 2 on C1, 3 on CalBOBL, 6 on Manta and 50 on PairoVET; (station, tow type, tow number) is unique) and tow_type. Declared in core_relationships() (calcofi4db 4.28.0), beside fish. Every two-net tow is one S and one P. fish itself is unchanged (10,796 rows identical to v2026.10.19).

The cruise reference is the union of SWFSC's dbo and stg schemas

"You now have the union of my stg and dbo cruises" (Ed Weber, 2026-10-14; swfsc_ichthyo Q23). Cruise.csv goes 694 → 739 rows, 50 of them with no station: the two cruises whose ichthyoplankton are back in staging (198202JD, 198212JD — the ingest now asserts they have no Station, Tow or Net row rather than no Cruise row), CUFES-only cruises, and cruises only the bottle and CTD sources sample. Consequences in cruise:

• 21 keys that v2026.10.19 completed as cruise_key_method = 'derived' rows (1952-09 BD, 1989-08 NH, and 19 bottle/CTD cruises from 2016-11 to 2025-07) are now swfsc rows with a cruise_uuid; derived falls from 151 to 130, mostly 1949–1959 cruises.
• A reference row with no station has no tow span, and the 21 above would have lost the span their derived row carried. complete_cruise_reference() (calcofi4db 4.28.0) now fills a NULL span from the events the other datasets key to the cruise, before adding any derived row, so check 6 of check_cruise_key_integrity() (an event within its cruise's span) keeps covering them. A row with its own tow span keeps it; a row no dataset keys to stays NULL.
• The 40 cce-lter_euphausiids tows of February 1982 key 1982-02-31JD again (they resolved no cruise in v2026.10.05–v2026.10.19); the release's NULL-cruise_key ratchet for that dataset returns to 420.
• 24 brand-new SWFSC keys with no event in any dataset (e.g. 1993-09-31M4 beside 1993-09-31JD, and the Lasker's 2019-07, 2021-03, 2021-07, 2022-07).

Nine net-less tows and the egg stages 12–15 are gone at source; two proportions sorted corrected

• Tow 74,394 → 74,385: the nine CalBOBL tows with no Net row "were all spoiled samples, spilled samples, or lost vials. They are now removed" (swfsc_ichthyo Q21). They carried no observation and no effort, so sample loses nine tow rows (1978-08 VA, 1982-03 PN, 1985-05 JD ×2, 1999-08 NH, 2007-04 JD, 2011-04 FR, 2012-03 SH, 2021-01 RL) and nothing else; true-zero tows go 6,302 → 6,293. Three of them were their station's only tow, so three site rows (1978-08-57VA 136.7 023.0, 1982-03-90PN 093.3 035.0, 2021-01-33UD 080.0 060.0) now have no tow and a NULL datetime, as the stations of the 15 tow-less cruises already did.
• EggStage 18,914 → 18,245: every stage 12–15 row is removed at source — anchovy and sardine stage 12 was "a lazy, stupid hack that they did to flag some records for DEPM", and the Dover and Rex sole rows go with them (Q22). The ingest already screened them out, so the published stage distribution is unchanged; the screen is now a guard that expects zero rows.
• Two C1 nets' PropSorted 3.4 → 0.294 and 4.286 → 0.233, and their SmallPlankton 10 → 34 and 7 → 30 ml (Q21): sample_measurement prop_sorted and small_plankton_biomass change on those two nets and nowhere else (every other sample_measurement value of the dataset is identical). The five "empty bongo tows with no zooplankton volume" are port-net-only tows, and a port net carries no zooplankton volume by design ("I don't have any non-port bongo tows in the db without zooplankton volumes"); the ingest now counts a missing volume on non-port nets only (0).
• Cufes 202101 RL sample 100: StopPumpSpeed 40.0 → 0.64 (swfsc_cufes Q10), so that sample's pump_speed_mean and volume_pumped_m3 change and its one non-zero egg_concentration (squid) goes 0.00113 → 0.0360 eggs/m³ (×31.75); its five other counts are zero. That is the only CUFES value that changes: all 550,162 obs_bio rows pair with v2026.10.19 once the squid key is mapped.

NetDepth is the estimated depth with all wire out, and the stations where it is below the sea floor go back to SWFSC

"It is the estimated depth when all wire is out. It is roughly the maximum depth of the tow but that estimate might be a little off. The 'possible' sounds too certain here" (Ed Weber, 2026-10-14; swfsc_ichthyo Q19). Every description that said "maximum possible depth" now says this; the data (sample.depth_max_m on tows and nets) and the release's own ratchet (210 stations more than 10 m below the deepest GEBCO cell around them) are unchanged, because Net.NetDepth is unchanged in the export. Those 210 stations, with their tow and net UUIDs, are in data/flagged/netdepth_below_seafloor.csv for SWFSC to screen ("If you send me the problems we can also try to screen some of these for errors").

fish is fish larger than larval size, counted in addition to the larvae

"They are fish larger than larvae size. So generally juveniles but not exclusively. They are not in both tables" (Ed Weber, 2026-10-14; swfsc_ichthyo Q20). The table stays (Ben Best, 2026-10-20, decision D3) and is described so: additive to the larval abundance of the same net and species code, never double-counted, and still not projected into obs because no life stage in the vocabulary says exactly "larger than larval size". The 974 orphan LarvaeMeasured rows and the 629 lost larval-stage records are "expected. Some of these may be reconstructed from paper sheets" (Q17, Q18): still flagged, still unreleased.

Other answers recorded

• CUFES "is ongoing. We cannot keep up with processing given our current staffing right now" (Q13); the record still ends 2022-04-27. The 37 CUFES samples with a start but no stop position are kept at their start position until SWFSC confirms whether "Yes to removing recs with no stop position" means them (Q14, proposed; decision D5).
• The five cruises with no station at v2026.10.05 "all have CUFES data … At least the last two have unprocessed staged tow data that will eventually be uploaded" (Q24).
• SWFSC rebuilt its ITIS and WoRMS lookups; taxon.scientific_name stays the WoRMS accepted name and dataset_taxon.ds_scientific_name SWFSC's verbatim name, as provenance (Q25; decision D4). Any code still keyed to another id than its source AphiaID is listed in data/flagged/species_worms_lookup_check.csv for SWFSC, never patched by an override.
• swfsc_ichthyo gains link_data_source (NOAA InPort item 20691, the provider's record of the database), so calcofi.io shows an "Original at" link for it.

A new dataset: calcofi_bottle-derived, spice and TEOS-10 sigma-theta at every bottle since 1949

Rasmus Swalethorp asked for values derived from the bottle database to live in a dataset of their own, back-calculated to the start of the record (thread "calcofi derived data", 2026-10-19), after Nastassia Patin asked for spice at each bottle depth. ingest_calcofi_bottle-derived.qmd computes two values per bottle from the bottle's own temperature and salinity, at the sea pressure of its depth (gsw_p_from_z(-depth, latitude)):

• spiciness0 (kg m⁻³), the same key and the same rule (ctd_spice()) as the CTD derived products. Filter on dataset_key to keep the bottle and CTD series apart. The registry row now lists both datasets in _source_datasets (Ben Best, decision D8).
• sigma_theta_teos10 (kg m⁻³), new: potential density anomaly at 0 dbar by TEOS-10 (gsw_sigma0), NERC P01 SIGTPR03. The bottle database's own sigma_theta is DECODR's legacy value and stays as it is in calcofi_bottle. The new key does not join its variable, because both come from the same bottles.

Flags come first: a bottle whose T_qual or S_qual is 8 or 9 gets neither value. A cruise whose input is known to be wrong is withheld by name: all 918 bottles of 2021-05-3322, whose published salinity equals its own sigma-theta, so the salinity column holds sigma-theta (calcofi_bottle Q13, open with the provider). A value we know is wrong never enters a derived product (Ben Best, 2026-10-20), and the cruise returns when Q13 is answered (Q03). Of 843,828 other bottles with a temperature and a salinity, 2,155 are flagged, so 841,673 bottles (1949-02-28 to 2021-02-03) carry both values, 1,683,346 obs_env rows. The dataset emits no sample; every row sits on its calcofi_bottle bottle. build_climatology() takes every obs_env row, so both types get baseline cells under this dataset_key. The rule is calcofi4db's new bottle_spice_sigma0() (4.27.0), and its tests compare it to the Gibbs SeaWater functions directly. The declared bound for sigma_theta_teos10 is −8 to 37 kg m⁻³: gsw_sigma0 over the registered bottle temperature and salinity bounds (Q02). spiciness0 keeps its −25 to 18 bound.

Over 839,590 bottles that also have an unflagged legacy value, TEOS-10 minus legacy is a median 0.0041 kg m⁻³ in absolute value (p99 0.0150, max 0.786). 10 bottles differ by more than 0.1 and are listed for the provider (Q03). Licence and PI inherit calcofi_bottle's open questions (Q01). ingest_calcofi_ctd-derived.qmd now merges into _source_datasets rather than overwriting it, so re-rendering it no longer drops the bottle dataset from spiciness0.

CalCOFI 2607's second temperature sensor is judged by the provider's own flags, and a sigma-theta computed from a flagged sensor is flagged

The 24 provisional flags on cruise 2026-07-3322 (casts 1-6, both directions, the secondary temperature sensor and the 11 series derived from it) are gone. We had set them on 2026-09-24 because the provider's cruise notes called the sensor faulty on all six casts; the provider's corrected file now carries its own codes (9 on casts 1U, 5U, 6D, 6U and 385 of the 515 bins of 5D) and Ben Gire wrote that the processed files are accurate. Casts 2-4 and the downcast of cast 1, which the provider leaves unflagged, therefore enter the sensor-pair averages again (the secondary reads about 0.15 degC from the primary there). Against v2026.10.19, from the provider's file: temperature_ave changes on 841 one-metre bins (at most 0.257 degC), salinity_ave_corr on 889 (0.370), oxygen_ml_l_ave_cruise_corr on 889 (0.222 ml/L), oxygen_ml_l_ave_sta_corr on 194 (0.281 ml/L) and oxygen_umol_kg_ave_sta_corr on 194 (12.31 umol/kg), and the derived spiciness0 on 889 bins (0.269). Of those bins, 151 (temperature), 157 (salinity and spiciness) and 41 (oxygen, sta_corr) sit at depths published in obs. The 12 sensor-2 series change only in measurement_qual on the bins the provider did not flag (9,864 values); no sensor-2 value changes, and nothing else outside 2607 moves for this change. Consumers: a 2607 anomaly or section built on these averages shifts by up to the amounts above.

Where the provider flags a temperature or salinity 8 or 9 it often leaves the sigma-theta computed from it unflagged (SigThetaTS2Q is blank on 2607 casts 1U, 5D and 6U where Temp2Q is 9), and the derived sigma_theta_ave and mixed-layer depths read only the sigma flags. A bad sensor's sigma-theta therefore entered the average. The ingest now writes the sensor's flag onto its sigma-theta (sigma_theta_1 from temperature_1 and salinity_1, sigma_theta_2 from the second pair; 9 over 8; the provider's own 8/9 is kept), after the provider's flags and before anything is averaged, and calcofi_ctd-derived asserts that no sigma_theta_ave includes a sensor whose sigma, temperature or salinity is flagged. Against v2026.10.19 this touches 28 cruises and 194 casts, 2607 included, and no sigma value changes: sigma_theta_1 gains a flag on 4,994 values (419 at depths published in obs) and sigma_theta_2 on 5,788 (not published in obs); sigma_theta_ave changes on 10,188 one-metre bins (at most 4.27 kg/m3, in 2005-07-32NM) and disappears on 413 where both sensors are now flagged (825 changed or removed at depths published in obs, 24 of them removed); the per-cast mld_sigma_theta_002 changes on 24 casts (at most 26.2 m) and mld_sigma_theta_0125 on 31 (at most 59.9 m), and each vanishes on 3 casts. The largest effects outside 2607 are 2016-11-33P4, 2012-07-32I1, 2018-02-3322, 2008-01-31JD, 2005-04-32NM, 2001-01-31JD, 2005-07-32NM and 2001-07-32NM. The climatology (1993-2013 baseline) moves on 336 monthly cells of sigma_theta_ave (at most 0.251 kg/m3), 221 of sigma_theta_1 (0.174), 16 of mld_sigma_theta_002 (5.95 m) and 23 of mld_sigma_theta_0125 (6.36 m); no cell appears or disappears. Consumers: sigma_theta_1 rows with measurement_qual 8 or 9 are now more numerous, so a query that does not apply cc_qual_ok_sql() / qual_ok_sql() / qualOkSQL() sees values it did not see flagged before, and a sigma_theta_ave anomaly on those cruises changes.

The bottle database's sigma_theta and r_dynamic_height are now described as legacy DECODR values: computed by the bottle database's old DECODR algorithm, which does not reproduce a Sea-Bird or TEOS-10 computation from the same temperature and salinity (Ben Gire, 2026-10-16). They are kept as published (Rasmus Swalethorp: "keep legacy, add modern, document"); no value changes. A TEOS-10 recomputation is planned as a separate dataset.

Eight CTD cruises from 1995–98 return: 9501JD, 9712SP and 9803SP–9812SP

These cruises had no CTD casts in any earlier release; they return with 368 casts and 320,384 obs_env rows from calcofi_ctd-cast (1995-01-31JD 134 casts and 125,232 rows; 1997-12-32QU 18 and 15,975; 1998-03-32QU 32 and 21,352; 1998-05-32QU 38 and 28,329; 1998-08-32QU 38 and 34,877; 1998-10-32QU 38 and 33,764; 1998-11-32QU 38 and 34,591; 1998-12-32QU 32 and 26,264). No other 1995–98 cruise changed against v2026.10.19. calcofi.org listed a final (CTDFinalQC) zip for each, but every one returned 404, so the ingest skipped it with only a warning, and it also skipped the cruise's CTDFinalDB copy on the Shared Drive (from JRW's pre-1998 archive) as a duplicate of the web final it never got. By 2026-10-20 calcofi.org lists only the raw zips for these cruises, so the CTDFinalDB copies are read (Ben Best, 2026-10-20). 19-9712SP_CTDFinalDB writes cast 005d at 521 m twice, 9 s apart; that one scan is recorded in the duplicate-scan ratchet as new coverage (1997-12-32QU = 1). The ingest now stops when a web final it means to read fails to download while its Shared Drive copy is skipped, so a cruise cannot vanish this way again. Whether CTDFinalDB is the record for these cruises is ctd-cast Q46, open with the CTD team.

Known issue: sixteen underway and meteorology keys carry no category

Re-running the calcofi_mets ingest for this release blanked the category of its own rows in metadata/measurement_type.csv: the notebook rebuilds the rows it owns and carried only the bounds and derivation across the rebuild. So in this release's measurement_type table and measurements.json, 16 keys have a NULL category. No value changed. calcofi.io gives such a key its dataset's category, Meteorology & Sea State, which is right for seven of them; until the next release, which carries the fix, sst_c, sss_psu, tsg1_temp_c, tsg1_salinity_psu, oxygen, uws_flow and bottom_depth_m show there instead of under Physical Oceanography, par_surf instead of Productivity & Pigments, and sw_ph instead of Carbonate System.

Contents (generated)

26 tables, 383,803,652 rows, 2.85 GB.

Datasets (20): calcofi_2022-edna, calcofi_bottle, calcofi_bottle-derived, calcofi_ctd-cast, calcofi_ctd-derived, calcofi_dic, calcofi_mets, calcofi_phyllosoma, calcofi_phytoplankton, cce-lter_euphausiids, cce-lter_iron, cce-lter_picoplankton-bacteria, cce-lter_zoodb, cce-lter_zooscan, cdfw_dungeness-crab, farallon_bird-mammal, sio_mesopelagic-fish, sio_pic-zooplankton, swfsc_cufes, swfsc_ichthyo

Validation: 97 pass / 0 fail / 4 skip (consumer-contract suite, 2026-10-21T03:44:12Z).

Software: calcofi4db 4.28.0, calcofi4r 1.28.0.

How to cite

CalCOFI (2026). CalCOFI Integrated Database, release v2026.10.20 [Data set]. Scripps Institution of Oceanography, NOAA Fisheries, and California Department of Fish and Wildlife. https://doi.org/10.5281/zenodo.23524400

Cite the source datasets you use alongside the release:

• calcofi_2022-edna — Patin N, ODonnell G (2026). CalCOFI October 2022 Vertebrate eDNA. Version 1.2. Occurrence dataset. https://doi.org/10.15468/n52j6r · CC-BY-4.0
• calcofi_bottle — CalCOFI. (2023). CalCOFI Bottle Database 194903-202105. CalCOFI.org. · license pending
• calcofi_bottle-derived — 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 · license pending
• calcofi_ctd-cast — CalCOFI. (2023). CalCOFI CTD Cast Files. CalCOFI.org. · license pending
• calcofi_ctd-derived — CalCOFI. (2026). CalCOFI CTD Derived Hydrographic Products (from the CalCOFI CTD Cast Files). CalCOFI.io. https://calcofi.io/workflows/ingest_calcofi_ctd-derived.html · license pending
• calcofi_dic — 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 · CC-BY-4.0
• calcofi_mets — CalCOFI. Underway (METS) TSG/Meteorology Data. CalCOFI.org. · license pending
• calcofi_phyllosoma — 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 · custom (https://portal.edirepository.org/nis/metadataviewer?packageid=knb-lter-cce.188.4)
• calcofi_phytoplankton — 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 · CC0-1.0 (https://creativecommons.org/publicdomain/zero/1.0/)
• cce-lter_euphausiids — 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 · custom (https://portal.edirepository.org/nis/metadataviewer?packageid=knb-lter-cce.313.1)
• cce-lter_iron — 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. · custom (https://portal.edirepository.org/nis/mapbrowse?packageid=knb-lter-cce.21.3)
• cce-lter_picoplankton-bacteria — Landry, M. (2004-2023). Picoplankton and Bacteria Abundance (CalCOFI Cruise). CCE LTER. · license pending
• cce-lter_zoodb — citation pending · custom (https://oceaninformatics.ucsd.edu/zoodb/)
• cce-lter_zooscan — citation pending · custom (https://oceaninformatics.ucsd.edu/zooscandb/)
• cdfw_dungeness-crab — 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. · CC-BY-4.0
• farallon_bird-mammal — citation pending · custom (https://oceanview.pfeg.noaa.gov/CalCOFI/app/resources/docs/Data_Sharing_Agreement_FarallonInstitute.pdf)
• sio_mesopelagic-fish — 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 · CC-BY-4.0
• sio_pic-zooplankton — citation pending · license pending
• swfsc_cufes — citation pending · custom (https://coastwatch.pfeg.noaa.gov/erddap/tabledap/erdCalCOFIcufes.das)
• swfsc_ichthyo — NOAA Fisheries SWFSC. CalCOFI Ichthyoplankton Database. · license pending

Access

con <- calcofi4r::cc_get_db(version = "v2026.10.20")

con = calcofi4py.cc_get_db("v2026.10.20")

Parquet: https://storage.googleapis.com/calcofi-db/ducklake/releases/v2026.10.20/parquet/{table}.parquet; full history: RELEASES.md.