# Sample Earth Tree Crop Reference Dataset: Coffee and Cocoa Samples, Colombia and Ghana

## Facts

- Provider: Alliance of Bioversity International and CIAT (Sample Earth)
- License: CC-BY-4.0 (https://source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh)
- Format: JPEG (in sampled files)
- Stored at: Amazon S3, s3://us-west-2.opendata.source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh (us-west-2)
- Access: public, readable without an account
- Category: Earth Observation & Geospatial
- Source: https://source.coop/alliance-bioversity-international-ciat/sample-earth-2026-co-gh
- Page: https://scigantic.com/archive/8f061b36-bd59-5270-912d-9b9259b662bb
- Keywords: Earth Observation & Geospatial, whole genome sequencing, satellite imagery, JPEG, AWS Open Data

## About

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.

## Load the data

```python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-west-2', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='us-west-2.opendata.source.coop', Prefix='alliance-bioversity-international-ciat/sample-earth-2026-co-gh/', Delimiter='/')
```

Lists the files with anonymous access. Runs on any machine, with no cloud account.

## Data structure

File types in sampled files: JPEG

Example file: `alliance-bioversity-international-ciat/sample-earth-2026-co-gh/README.md`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/8f061b36-bd59-5270-912d-9b9259b662bb
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/8f061b36-bd59-5270-912d-9b9259b662bb
- Over MCP: `get_schema_card` with id `8f061b36-bd59-5270-912d-9b9259b662bb` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [JPEG datasets](https://scigantic.com/topics/jpeg)
- [Whole genome sequencing datasets](https://scigantic.com/topics/whole-genome-sequencing)
