{"success":true,"data":{"author":"Google for the Forest Data Partnership; anonymous mirror by Portolan Mirrors","bucketAccessType":"public","bucketListable":true,"bucketName":"us-west-2.opendata.source.coop","bucketPrefix":"portolan-mirrors/forest-data-partnership-catalog","category":"Agriculture & Environment","cloudProvider":"aws","createdAt":"2026-11-18T17:37:22.778Z","description":"Per-pixel probability, from 0 to 1, that land is planted with cocoa, coffee, oil palm or rubber, at 10 m resolution, from the Forest Data Partnership community model release 2026a produced by Google, used for deforestation-free supply chain monitoring (for example under the EU Deforestation Regulation, EUDR). This mirror covers the West African cocoa belt for 2018 and 2024: 224 one-degree tiles per commodity and year from Sierra Leone to Gabon (15 W to 17 E, 1 S to 11 N), eight collections (cocoa-2018, cocoa-2024, coffee-, palm- and rubber-) of about 110 GiB each. Each item is a Float32 Cloud Optimized GeoTIFF of about 11,133 x 11,133 pixels in EPSG:4326 with a thumbnail, ids lng_<west>_lat_<south>, and each collection adds a pan-tropical overview COG of all 5,516 tiles at about 320 m and a STAC GeoParquet items.parquet. Tiles were copied unchanged from Google's requester-pays GCS bucket and checked against Google's MD5. Read with rasterio, GDAL /vsicurl/ or DuckDB. Licensed CC BY 4.0; attribute \"Produced by Google for the Forest Data Partnership\".","displayTitle":"Forest Data Partnership Commodity Probability Maps: Cocoa, Coffee, Oil Palm, Rubber at 10 m, 2018 and 2024 (model 2026a)","fuseMountBrowsable":true,"id":"bf5f8aac-e25d-5d9a-b349-1cc4289cbb8e","license":"CC-BY-4.0","licenseEvidenceUrl":"https://developers.google.com/earth-engine/guides/forest_data_partnership_gcs_readme","objectCountEstimate":8,"probeStatus":"ok","region":"us-west-2","schemaCard":{"accessHints":[{"language":"python-anonymous","snippet":"import boto3\nfrom botocore import UNSIGNED\nfrom botocore.client import Config\ns3 = boto3.client('s3', region_name='us-west-2', config=Config(signature_version=UNSIGNED))\ns3.list_objects_v2(Bucket='us-west-2.opendata.source.coop', Prefix='portolan-mirrors/forest-data-partnership-catalog/', Delimiter='/')"},{"language":"python-local","snippet":"open('/mnt/archive/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json', 'rb')"}],"caveats":["Files are binary — use a domain-specific parser (e.g. metpy / pynexrad / pydicom) rather than text I/O."],"format":"binary","generatedAt":"2026-11-18T17:39:27.374Z","layout":{"example":"portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json","pattern":"{prefix}/{seg1}/{seg2}/{seg3}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"{\n  \"type\": \"Feature\",\n  \"stac_version\": \"1.1.0\",\n  \"stac_extensions\": [\n    \"https://schemas.portolan-sdi.org/portolan/v0.2.0/schema.json\",\n    \"https://stac-extensions.github.io/file/v2.1.0/schema.json\",\n    \"https://stac-extensions.github.io/projection/v2.0.0/schema.json\",\n    \"https://stac-extensions.github.io/raster/v2.0.0/schema.json\",\n    \"https://stac-extensions.github.io/render/v2.0.0/schema.json\"\n  ],\n  \"id\": \"lng_-10_lat_10\",\n  \"geometry\": {\n    \"type\": \"Polygon\",\n    \"coordinates\": [\n      [\n   ","encoding":"utf8","key":"portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json","truncatedAt":512},{"bytes":"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","encoding":"hex","key":"portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.thumb.jpg","truncatedAt":512}],"sampleObjects":["portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json","portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.thumb.jpg","portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.tif"],"sidecars":[{"bytes":"# Commodity probability maps\n\nThe Forest Data Partnership commodity maps, mirrored on Source Cooperative.\n\nPer-pixel probability, from 0 to 1, that land is planted with cocoa, coffee, oil palm\nor rubber, at 10 m resolution, from the Forest Data Partnership community model\nrelease 2026a, produced by Google.\n\n## What is here\n\nThe West African cocoa belt for 2018 and 2024: 224 one-degree tiles per commodity and\nyear, from Sierra Leone to Gabon (15°W–17°E, 1°S–11°N, land south of 10°N). One\ncollection per commodity and year, eight in total:\n\n| Collection | Items | Size |\n|---|---|---|\n| `cocoa-2018`, `cocoa-2024` | 224 each | 110.1 and 110.2 GiB |\n| `coffee-2018`, `coffee-2024` | 224 each | 109.4 and 109.6 GiB |\n| `palm-2018`, `palm-2024` | 224 each | 110.0 and 109.8 GiB |\n| `rubber-2018`, `rubber-2024` | 224 each | 108.6 and 108.6 GiB |\n\nEach item is one Cloud-Optimized GeoTIFF of about 11133 × 11133 Float32 pixels in\nEPSG:4326, with a 347 px thumbnail. Item ids (`lng_<west>_lat_<south>`) are the same\nin every collection, so a tile can be compared across commodities and years.\n\nEach collection also has a **pan-tropical overview**: one COG of all 5,516 tiles\nof the release for that commodity and year (24°S–24°N) at about 320 m, 2.5 to 2.6 GB.\nIt serves maps below zoom 9 and coarse statistics. Every collection publishes its\nitems as STAC GeoParquet (`items.parquet`).\n\n## License\n\n[CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). Attribute as:\n\"Produced by Google for the Forest Data Partnership.\"\n\n## Provenance\n\nThis catalog is a mirror, not the official publication. Google publishes the files\nin a requester-pays Google Cloud Storage bucket,\n`gs://earth-engine-public-requester-pays/forestdatapartnership`, documented at\nhttps://developers.google.com/earth-engine/guides/forest_data_partnership_gcs_readme.\nThere, every read is billed to the reader and browsers cannot read the files.\n\nThe tiles were copied unchanged on 2026-10-10 (2024 at 17:10 UTC, 2018 at\n18:12 UTC). Each item's `file:checksum` is Google's MD5 for the file, and random\nanonymous downloads were checked byte for byte against it. The overviews are\nderived files, built from the 347 px level that Google publishes inside each tile.\nThe catalog's source, generator and issue tracker are at\nhttps://github.com/portolan-mirrors/forest-data-partnership-catalog.\n\nModel method and limitations:\nhttps://github.com/google/forest-data-partnership/tree/main/models/model_2026a\n\n## Access\n\nFind the tiles that cover a point, with one request, in DuckDB:\n\n```sql\nINSTALL httpfs; LOAD httpfs;\nSELECT id, title\nFROM read_parquet('https://data.source.coop/portolan-mirrors/forest-data-partnership-catalog/cocoa-2024/items.parquet')\nWHERE bbox.xmin <= -1.5 AND bbox.xmax >= -1.5 AND bbox.ymin <= 6.5 AND bbox.ymax >= 6.5;\n```\n\nRead one tile without downloading it, in QGIS or GDAL:\n\n```sh\ngdalinfo /vsicurl/https://data.source.coop/portolan-mirrors/forest-data-partnership-catalog/cocoa-2024/lng_-2_lat_6/lng_-2_lat_6.tif\n```\n","encoding":"utf8","key":"portolan-mirrors/forest-data-partnership-catalog/README.md","name":"README.md","size":3025,"truncated":false},{"bytes":"{\n  \"type\": \"Catalog\",\n  \"stac_version\": \"1.1.0\",\n  \"stac_extensions\": [\n    \"https://schemas.portolan-sdi.org/portolan/v0.2.0/schema.json\"\n  ],\n  \"id\": \"forest-data-partnership\",\n  \"title\": \"Forest Data Partnership commodity maps (Source Cooperative mirror)\",\n  \"description\": \"Per-pixel probability that land is planted with cocoa, coffee, oil palm or rubber, at 10 m, from the Forest Data Partnership community model release 2026a, produced by Google. This mirror holds the West African cocoa belt for 2018, 2024: one collection per commodity and year, 1792 Cloud-Optimized GeoTIFFs copied unchanged from Google's requester-pays bucket and served over plain HTTPS, with pan-tropical overviews for low zoom. Attribution: \\\"Produced by Google for the Forest Data Partnership.\\\"\",\n  \"links\": [\n    {\n      \"rel\": \"root\",\n      \"href\": \"./catalog.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Catalog root\"\n    },\n    {\n      \"rel\": \"self\",\n      \"href\": \"https://data.source.coop/portolan-mirrors/forest-data-partnership-catalog/catalog.json\",\n      \"type\": \"application/json\",\n      \"title\": \"This catalog, as published\"\n    },\n    {\n      \"rel\": \"describedby\",\n      \"href\": \"./README.md\",\n      \"type\": \"text/markdown\",\n      \"title\": \"Catalog README\"\n    },\n    {\n      \"rel\": \"agents\",\n      \"href\": \"./AGENTS.md\",\n      \"type\": \"text/markdown\",\n      \"title\": \"Catalog agent guide\"\n    },\n    {\n      \"rel\": \"license\",\n      \"href\": \"https://creativecommons.org/licenses/by/4.0/\",\n      \"type\": \"text/html\",\n      \"title\": \"CC-BY-4.0\"\n    },\n    {\n      \"rel\": \"via\",\n      \"href\": \"https://developers.google.com/earth-engine/datasets/publisher/forestdatapartnership\",\n      \"type\": \"text/html\",\n      \"title\": \"Forest Data Partnership in the Earth Engine data catalog\"\n    },\n    {\n      \"rel\": \"vcs\",\n      \"href\": \"https://github.com/portolan-mirrors/forest-data-partnership-catalog\",\n      \"title\": \"Source repository\"\n    },\n    {\n      \"rel\": \"issues\",\n      \"href\": \"https://github.com/portolan-mirrors/forest-data-partnership-catalog/issues\",\n      \"title\": \"Issue tracker\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./cocoa-2018/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Cocoa probability 2018 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./coffee-2018/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Coffee probability 2018 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./palm-2018/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Oil palm probability 2018 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./rubber-2018/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Rubber probability 2018 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./cocoa-2024/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Cocoa probability 2024 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./coffee-2024/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Coffee probability 2024 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./palm-2024/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Oil palm probability 2024 (Forest Data Partnership model 2026a)\"\n    },\n    {\n      \"rel\": \"child\",\n      \"href\": \"./rubber-2024/collection.json\",\n      \"type\": \"application/json\",\n      \"title\": \"Rubber probability 2024 (Forest Data Partnership model 2026a)\"\n    }\n  ],\n  \"updated\": \"2026-10-10T18:12:15Z\"\n}\n","encoding":"utf8","key":"portolan-mirrors/forest-data-partnership-catalog/catalog.json","name":"catalog.json","size":3704,"truncated":false},{"bytes":"# Cocoa probability, 2018\n\nCocoa probability 2018 (Forest Data Partnership model 2026a).\n\nPer-pixel probability, from 0 to 1, that the pixel includes cocoa trees in 2018, at 10 m resolution.\n\nGhana and Côte d'Ivoire are the two largest cocoa producers in the world and the best-sampled region in the cocoa reference database. It includes the WRI West Africa Cocoa dataset of about 760,000 GPS-traced plots, CIAT plot data in Ghana, CERSGIS field data from a Lacuna Fund project, and field points collected across Ghana, Côte d'Ivoire, Liberia and Sierra Leone.\n\nMeasured from the tiles' 2783 px overview level (about 40 m): tile means range from 0.000 to 0.672, with a median of 0.005, and 41 of 224 tiles have a mean of 0.1 or more.\n\nThe Forest Data Partnership (https://developers.google.com/earth-engine/datasets/publisher/forestdatapartnership) is a collaboration on global monitoring of deforestation, degradation and restoration linked to commodity production. It is coordinated with the FAO (https://www.fao.org/in-action/forest-data-partnership) and its reference data come from contributors such as the FAO, WRI, CIAT, MapBiomas, SERVIR, IIASA and Google. Google produces the community models: a deep learning model trained on the AlphaEarth Foundation annual satellite embeddings (64 features per 10 m pixel) with millions of community-sourced reference points. Release 2026a covers the pan-tropical belt from 24°S to 24°N for 2018, 2020, 2022 and 2024, and adds input data, bug fixes and a reworked processing pipeline over release 2025b. The maps are per-pixel probabilities, so users choose a threshold for their purpose, such as commodity supply-chain and deforestation-regulation checks. The datasets are not yet peer reviewed. Method and limitations: https://github.com/google/forest-data-partnership/tree/main/models/model_2026a\n\nThis collection mirrors the 224 one-degree tiles of release 2026a for 2018 that touch the West African cocoa belt: land in Sierra Leone, Liberia, Guinea, Côte d'Ivoire, Ghana, Togo, Benin, Nigeria, Cameroon, Equatorial Guinea and Gabon south of 10°N, between 15°W and 17°E and between 1°S and 11°N. The files are copied unchanged from Google's requester-pays bucket, byte for byte, and each item records Google's MD5 for the file. Each tile is one item with one Cloud-Optimized GeoTIFF of about 11133 by 11133 Float32 pixels in EPSG:4326. The same tiles exist for cocoa, coffee, oil palm and rubber, with identical item ids, and for each mirrored year.\n\n## License and attribution\n\n[CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). Attribute as: \"Produced by Google for the Forest Data Partnership.\"\n\n## Provenance\n\n- Source: `gs://earth-engine-public-requester-pays/forestdatapartnership/2026a/cocoa/2018/` (Google Cloud Storage, requester pays).\n- Copied unchanged to Source Cooperative on 2026-10-10. Each item's `file:checksum` is Google's MD5 for the file, as a multihash.\n- Band statistics come from each tile's 2783 px overview level. They are approximate.\n\n## Files\n\n| File | What it is |\n|---|---|\n| `<tile>/<tile>.tif` | 224 Cloud-Optimized GeoTIFFs, one per one-degree tile |\n| `<tile>/<tile>.thumb.jpg` | 347 px preview of each tile, YlGn ramp |\n| `<tile>/<tile>.json` | STAC item of each tile |\n| `items.parquet` | all items as STAC GeoParquet, for one-request queries |\n| `cocoa-2018_overview.tif` | pan-tropical overview at about 320 m, for maps below zoom 9 |\n\nBrowse: https://source.coop/portolan-mirrors/forest-data-partnership-catalog/cocoa-2018\n","encoding":"utf8","key":"portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/README.md","name":"README.md","size":3531,"truncated":false}],"sourceObjectKey":"portolan-mirrors/forest-data-partnership-catalog/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json","starterCell":"with open('/mnt/archive/cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.json', 'rb') as fh:\n    head = fh.read(1024)\nprint(len(head), head[:64])","starterSamplePath":"cocoa-2018/lng_-10_lat_10/lng_-10_lat_10.thumb.jpg","totalObjects":"8 top-level prefixes"},"summary":"Per-pixel probability, from 0 to 1, that land is planted with cocoa, coffee, oil palm or rubber, at 10 m resolution, from the Forest Data Partnership community model release 2026a…","title":"Forest Data Partnership Commodity Probability Maps: Cocoa, Coffee, Oil Palm, Rubber at 10 m, 2018 and 2024 (model 2026a)","updatedAt":"2026-11-18T18:53:51.302Z","visibility":"public","websiteUrl":"https://developers.google.com/earth-engine/guides/forest_data_partnership_gcs_readme"}}