{
  "dataset_key": "sio_cetacean-sonobuoy",
  "provider": {
    "key": "sio",
    "short": "SIO",
    "name": "Scripps Institution of Oceanography, UC San Diego",
    "url": "https://scripps.ucsd.edu",
    "registered": true
  },
  "dataset": "cetacean-sonobuoy",
  "dataset_name": "CalCOFI Sonobuoy Baleen Whale Call Detections",
  "dataset_name_short": "Whale calls (sonobuoy)",
  "category": {
    "name": "Seabirds & Marine Mammals",
    "realm": "bio",
    "icon": "cat-birds-mammals",
    "order": 12,
    "description": "Strip-transect counts of seabirds and marine mammals along the cruise track",
    "registered": true
  },
  "color": "#3f8f8b",
  "visibility": "public",
  "description_md": "Hourly presence of blue, fin and humpback whale calls in sonobuoy recordings from CalCOFI cruises, 2004-2012. Each record is one hour of a DIFAR or omnidirectional sonobuoy deployment near a CalCOFI station, scanned by an analyst as 60-second spectrogram windows, with the call types heard. Curated by the Scripps Whale Acoustics Lab (Baumann-Pickering) and staged from the CalCOFI marine mammal Shiny app repository (CalCOFI/marmam-app). The hydrophone depth is not recorded (the DIFAR or omnidirectional setting is not given), so sample and observation depths are empty, not 0 m. Hours scanned only for a few calls (\"adhoc only\") are kept as samples with no presence value.\n",
  "keywords": [
    "EARTH SCIENCE > BIOLOGICAL CLASSIFICATION > ANIMALS/VERTEBRATES > MAMMALS",
    "Marine Turtles, Birds, and Mammals"
  ],
  "attribution": {
    "citation_main": null,
    "citation_others": [],
    "doi": null,
    "license": "unknown",
    "license_name": "Not yet established",
    "license_url": null,
    "acknowledgement": null,
    "contact": null,
    "pi_names": [
      "Simone Baumann-Pickering",
      "John Hildebrand"
    ],
    "creators": [
      {
        "name": "Simone Baumann-Pickering",
        "organization": "UCSD SIO",
        "orcid": null,
        "email": null,
        "role": "lead"
      }
    ],
    "funding": null,
    "source_accessed": "2026-10-04"
  },
  "links": {
    "calcofi_org": null,
    "data_source": "https://github.com/CalCOFI/marmam-app/tree/main/data/acoustic_data",
    "workflow": "https://calcofi.io/workflows/ingest_sio_cetacean-sonobuoy.html",
    "page": "https://calcofi.io/datasets/sio_cetacean-sonobuoy/"
  },
  "coverage": {
    "realm": "bio",
    "temporal": "2004-03 to 2012-11",
    "year_min": 2004,
    "year_max": 2012,
    "years": [
      {
        "year": 2004,
        "n_obs": 918,
        "n_roots": 84
      },
      {
        "year": 2005,
        "n_obs": 1086,
        "n_roots": 120
      },
      {
        "year": 2006,
        "n_obs": 1056,
        "n_roots": 126
      },
      {
        "year": 2007,
        "n_obs": 786,
        "n_roots": 90
      },
      {
        "year": 2008,
        "n_obs": 768,
        "n_roots": 92
      },
      {
        "year": 2009,
        "n_obs": 909,
        "n_roots": 107
      },
      {
        "year": 2010,
        "n_obs": 1527,
        "n_roots": 137
      },
      {
        "year": 2011,
        "n_obs": 1047,
        "n_roots": 106
      },
      {
        "year": 2012,
        "n_obs": 1173,
        "n_roots": 96
      }
    ],
    "spatial": "29.8–37.6°N, 124.6–117.3°W",
    "bbox": {
      "lat_min": 29.8464,
      "lat_max": 37.6141,
      "lon_min": -124.6293,
      "lon_max": -117.2573
    },
    "bbox_robust": {
      "lat_min": 30.1797057592667,
      "lat_max": 35.2771356763271,
      "lon_min": -124.170527150319,
      "lon_max": -117.872721266159,
      "n_positions": 8865
    },
    "months": [
      1365,
      624,
      624,
      1749,
      0,
      39,
      1752,
      927,
      0,
      741,
      1449,
      0
    ],
    "n_obs": 9270,
    "n_roots": 958,
    "n_stations": 92,
    "n_variables": 1,
    "n_taxa": 3,
    "depth_min_m": null,
    "depth_max_m": null,
    "variables": [
      {
        "name": "acoustic_presence",
        "units": "dimensionless",
        "uri": null,
        "category": "Seabirds & Marine Mammals"
      }
    ],
    "taxa": [
      {
        "taxon_key": "worms:137090",
        "scientific_name": "Balaenoptera musculus",
        "common_name": "Blue Whale",
        "rank": "Species",
        "n_obs": 3090
      },
      {
        "taxon_key": "worms:137091",
        "scientific_name": "Balaenoptera physalus",
        "common_name": "Fin Whale",
        "rank": "Species",
        "n_obs": 3090
      },
      {
        "taxon_key": "worms:137092",
        "scientific_name": "Megaptera novaeangliae",
        "common_name": "Humpback Whale",
        "rank": "Species",
        "n_obs": 3090
      }
    ],
    "life_stages": [],
    "contributes_to": []
  },
  "tables": [
    "sample",
    "obs",
    "obs_attribute",
    "taxon",
    "dataset_taxon",
    "taxon_group",
    "measurement_type"
  ],
  "objects": [
    {
      "table": "obs",
      "scope": "partition",
      "shared": false,
      "path": "ducklake/tables/obs/dataset_key=sio_cetacean-sonobuoy/09009af8bfff2df6b3a0e661/data_0.parquet",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/obs/dataset_key=sio_cetacean-sonobuoy/09009af8bfff2df6b3a0e661/data_0.parquet",
      "table_description": "The occurrence-headline long table: one scalar measurement per row, environmental (`realm = 'env'`) and biological (`realm = 'bio'`) together.",
      "bytes": 49754,
      "sha256": "3f1a57ad2c1fed6ce8028280e4ee1c6ba84cef4017914677ac10ea76f0b665ba",
      "since": "v2026.10.05"
    },
    {
      "table": "taxon_group",
      "scope": "table",
      "shared": true,
      "path": "ducklake/tables/taxon_group/746bd4e08194e98f2f69fbf5/taxon_group.parquet",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/taxon_group/746bd4e08194e98f2f69fbf5/taxon_group.parquet",
      "table_description": "Portable groupings of taxa (phytoplankton functional groups, seabirds, marine mammals).",
      "bytes": 2764,
      "sha256": "1f8a8f4ae8338ed85cb543b76e5599834cea81043548e19cb05766b8b2551259",
      "since": "v2026.10.05"
    }
  ],
  "since_version": "v2026.10.05",
  "distributions": [
    {
      "kind": "service",
      "url": "https://storage.googleapis.com/calcofi-db/stac/collections/sio_cetacean-sonobuoy/collection.json",
      "format": "stac",
      "id": "sio_cetacean-sonobuoy",
      "title": "STAC collection",
      "status": "current"
    },
    {
      "kind": "download",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/obs/dataset_key=sio_cetacean-sonobuoy/09009af8bfff2df6b3a0e661/data_0.parquet",
      "format": "parquet",
      "table": "obs",
      "scope": "partition",
      "shared": false,
      "title": "obs (this dataset's rows)",
      "table_description": "The occurrence-headline long table: one scalar measurement per row, environmental (`realm = 'env'`) and biological (`realm = 'bio'`) together.",
      "bytes": 49754,
      "sha256": "3f1a57ad2c1fed6ce8028280e4ee1c6ba84cef4017914677ac10ea76f0b665ba",
      "since": "v2026.10.05",
      "status": "current"
    },
    {
      "kind": "download",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/taxon_group/746bd4e08194e98f2f69fbf5/taxon_group.parquet",
      "format": "parquet",
      "table": "taxon_group",
      "scope": "table",
      "shared": true,
      "title": "taxon_group (whole table)",
      "table_description": "Portable groupings of taxa (phytoplankton functional groups, seabirds, marine mammals).",
      "bytes": 2764,
      "sha256": "1f8a8f4ae8338ed85cb543b76e5599834cea81043548e19cb05766b8b2551259",
      "since": "v2026.10.05",
      "status": "current"
    },
    {
      "kind": "notebook",
      "url": "https://calcofi.io/workflows/ingest_sio_cetacean-sonobuoy.html",
      "format": "html",
      "title": "ingest notebook",
      "status": "current"
    },
    {
      "kind": "source",
      "url": "https://github.com/CalCOFI/marmam-app/tree/main/data/acoustic_data",
      "portal": "other",
      "title": "source",
      "status": "external"
    }
  ],
  "registrations": [
    {
      "portal": "erddap",
      "status": "planned",
      "issues": []
    },
    {
      "portal": "obis",
      "status": "planned",
      "issues": []
    },
    {
      "portal": "edi",
      "status": "planned",
      "issues": []
    },
    {
      "portal": "ncei",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "caloos",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "zenodo",
      "status": "published",
      "url": "https://doi.org/10.5281/zenodo.22281994",
      "id": "10.5281/zenodo.22281994",
      "title": "CalCOFI Integrated Database (the release deposit)",
      "note": "as part of the integrated database release"
    }
  ],
  "status": {
    "stage": "validated",
    "priority": "should-complete",
    "gh_issue": null,
    "blockers": "Re-rendered and validated 2026-10-01; un-held 2026-10-04 (ships in the next release, licence pending). 962 deployments, 3,244 analysed hours, 9,270 acoustic_presence obs; cruise_key on every hour. Date/Hour read as UTC from same-station release samples (Q04 proposed). Open: licence Q01, citation Q02, background codes Q11, post-2012 Q12, CC0907MA blue whale gap Q13, hydrophone depth (now NULL, not 0 m).",
    "publish_policy": "Archive of record: none known; the source is the lab's spreadsheet copied into CalCOFI/marmam-app.",
    "updated": "2026-10-01",
    "questions_open": 13,
    "questions_dataset": [
      {
        "label": "Q01",
        "field": "license",
        "status": "open"
      },
      {
        "label": "Q02",
        "field": "citation_main",
        "status": "open"
      },
      {
        "label": "Q03",
        "field": "pi_names",
        "status": "proposed"
      }
    ]
  }
}