{"success":true,"data":{"author":"Alliance of Bioversity International and CIAT (Sample Earth)","bucketAccessType":"public","bucketListable":true,"bucketName":"us-west-2.opendata.source.coop","bucketPrefix":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh","category":"Earth Observation & Geospatial","cloudProvider":"aws","createdAt":"2026-11-16T15:39:54.096Z","description":"Land-cover reference samples for training and validating coffee and cocoa maps, from the Sample Earth initiative of the Alliance of Bioversity International and CIAT, produced with Google support. Experts interpreted very high resolution satellite imagery inside 600 m x 600 m sampling cells and labelled polygons and points with four classes: coffee, cocoa, other tree crops (including bamboo) and seasonal agriculture. ghana.gpkg covers 258 sampling sites with 6,277 polygons and 13,366 points on imagery from 2021-12 to 2025-11; colombia.gpkg covers 147 sites with 6,672 polygons and 12,272 points on imagery from 2020-10 to 2025-09. Each GeoPackage (WGS 84, EPSG:4326) has four tables: land-cover-legend, sampling-area cell centres with imagery dates, and the labelled polygon and point layers. Quality-controlled labels support commodity crop mapping for the EU Deforestation Regulation (EUDR), deforestation-free supply chain monitoring, agroforestry and land-use studies. Read with geopandas or GDAL. Licensed CC BY 4.0; cite Alliance Bioversity-CIAT Sample Earth.","displayTitle":"Sample Earth Tree Crop Reference Dataset: Coffee and Cocoa Samples, Colombia and Ghana","fuseMountBrowsable":true,"id":"8f061b36-bd59-5270-912d-9b9259b662bb","license":"CC-BY-4.0","licenseEvidenceUrl":"https://source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh","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='alliance-bioversity-international-ciat/sample-earth-2026-co-gh/', Delimiter='/')"},{"language":"python-local","snippet":"open('/mnt/archive/README.md', 'rb')"}],"caveats":["Bucket has a flat key structure (no prefix folders). Avoid unbounded LIST — page with ContinuationToken or filter by key prefix.","Files are binary — use a domain-specific parser (e.g. metpy / pynexrad / pydicom) rather than text I/O."],"format":"binary","generatedAt":"2026-11-16T15:39:56.741Z","layout":{"example":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md","pattern":"{prefix}/{seg1}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"# Sample Earth: Tree Crop Reference Dataset\n\n[![DOI](https://img.shields.io/badge/DOI-10.60480%2Fmjsk--yg88-lightgray)](https://doi.org/10.60480/mjsk-yg88)\n\nThis dataset is part of the [Sample Earth](https://cgspace.cgiar.org/items/73040655-ce35-4f4e-8126-4527703cc5f3) initiative, a global effort to build open, high-quality reference data for improving the accuracy and inclusiveness of land-cover maps.\n\nThis dataset contains GPS-located land-cover samples that can be used to train and validate AI models tha","encoding":"utf8","key":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md","truncatedAt":512},{"bytes":"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","encoding":"hex","key":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh/colombia.gpkg","truncatedAt":512}],"sampleObjects":["alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md","alliance-bioversity-international-ciat/sample-earth-2026-co-gh/colombia.gpkg","alliance-bioversity-international-ciat/sample-earth-2026-co-gh/ghana.gpkg","alliance-bioversity-international-ciat/sample-earth-2026-co-gh/qgis_preview.qgz","alliance-bioversity-international-ciat/sample-earth-2026-co-gh/sample-earth-tree-crops.jpg"],"sidecars":[{"bytes":"# Sample Earth: Tree Crop Reference Dataset\n\n[![DOI](https://img.shields.io/badge/DOI-10.60480%2Fmjsk--yg88-lightgray)](https://doi.org/10.60480/mjsk-yg88)\n\nThis dataset is part of the [Sample Earth](https://cgspace.cgiar.org/items/73040655-ce35-4f4e-8126-4527703cc5f3) initiative, a global effort to build open, high-quality reference data for improving the accuracy and inclusiveness of land-cover maps.\n\nThis dataset contains GPS-located land-cover samples that can be used to train and validate AI models that generate detailed, accurate maps, with a focus on coffee and cocoa production systems.  The data were collected across Colombia and Ghana through expert interpretation of high-resolution satellite imagery. Each sample is labelled and quality-controlled to represent the land-cover types. The classification scheme includes four main classes: coffee, cocoa, tree crops, and seasonal agriculture.\n\nWhile the primary goal is to distinguish coffee and cocoa systems from other land uses, the dataset also supports broader applications such as agricultural monitoring, deforestation analysis, ecosystem-service mapping, land-use planning, and suitability modelling.\n\nBy providing transparent, well-validated training data, this dataset contributes to Sample Earth's broader objective: strengthening AI-based land monitoring tools and supporting global efforts, including the EU Deforestation Regulation (EUDR), to ensure sustainable, deforestation-free agricultural supply chains.\n\nThe dataset is designed to grow continuously, incorporating new commodities, timeframes, and countries over time.\n\nThis dataset was produced with the support of Google.\n\n## Sample annotated ROI\n\n![sample annotation](https://data.source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh/sample-earth-tree-crops.jpg)\n\n## Files\n\n| File | Country | Sampling Sites | Polygons count| Points count | Imagery date range |\n|---|---|---|---|---|---|\n| `ghana.gpkg` | Ghana | 258 | 6,277 | 13,366 | 2021-12-18 – 2025-11-23 |\n| `colombia.gpkg` | Colombia | 147 | 6,672 | 12,272 | 2020-10-13 – 2025-09-10 |\n\nBoth GeoPackages use the WGS 84 (EPSG:4326) coordinate reference system and are licensed under CC BY 4.0.\n\n## Tables\n\nEach GeoPackage contains four tables:\n\n### `land-cover-legend`\n\nAttribute table containing the land cover classification legend.\n\n| `land_cover_id` | `name` | `description` |\n|---|---|---|\n| 0 | Coffee | Plantation containing coffee and any other crops |\n| 1 | Cocoa | Plantation containing cocoa and any other plots |\n| 2 | Tree crops | Tree crops plantation (including bamboo) without coffee or cocoa |\n| 3 | Seasonal agriculture | Seasonal agriculture |\n\n### `sampling-area`\n\nPoint geometry layer representing the centre of each sampling area cell. Each cell defines a 600 m × 600 m area within which imagery interpretation was conducted.\n\n| Field | Type | Description |\n|---|---|---|\n| `fid` | Integer | Auto-increment primary key |\n| `geom` | Point | Centre point of the sampling area cell |\n| `cell_uuid` | Text | Unique identifier of the sampling area cell |\n| `imagery_date` | Date | Date of the satellite imagery used for interpretation in this cell |\n\n### `polygon-collection`\n\nMultiPolygon geometry layer containing exhaustive land cover delineations within each sampling area. Around each selected sampling area centre, within the 600 m extent, all cocoa, coffee, tree crops (orchards/bamboo), and seasonal agriculture pixels were mapped as polygons. Therefore, any non-annotated pixel within a sampling area can be assigned to the remaining (other) land cover categories. In other words, the polygon collection represents a complete annotation of the target classes within each cell.\n\n| Field | Type | Description |\n|---|---|---|\n| `fid` | Integer | Auto-increment primary key |\n| `geom` | MultiPolygon | Delineated land cover polygon |\n| `sample_uuid` | Text | Unique identifier for this polygon sample |\n| `cell_uuid` | Text | Foreign key linking to the corresponding `sampling-area` cell |\n| `land_cover_id` | Integer | Land cover class (see `land-cover","encoding":"utf8","key":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md","name":"README.md","size":11759,"truncated":true}],"sourceObjectKey":"alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md","starterCell":"with open('/mnt/archive/README.md', 'rb') as fh:\n    head = fh.read(1024)\nprint(len(head), head[:64])","starterSamplePath":"sample-earth-tree-crops.jpg","totalObjects":"flat keyspace (count unknown from bounded probe)"},"summary":"Land-cover reference samples for training and validating coffee and cocoa maps, from the Sample Earth initiative of the Alliance of Bioversity International and CIAT, produced…","title":"Sample Earth Tree Crop Reference Dataset: Coffee and Cocoa Samples, Colombia and Ghana","updatedAt":"2026-11-17T17:12:20.414Z","visibility":"public","websiteUrl":"https://source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh"}}