# Great African Food Company Tanzania Ground Reference Crop Type Dataset with Sentinel-2 time series, 2018 (Radiant Earth MLHub)

## Facts

- Provider: Great African Food Company; Radiant Earth Foundation
- License: CC-BY-4.0 (https://api.datacite.org/dois/10.34911/rdnt.5vx40r)
- Format: TIFF (in sampled files)
- Stored at: Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/african-crops-01/tanzania
- Access: public, readable without an account
- DOI: https://doi.org/10.34911/rdnt.5vx40r
- Category: Earth Observation & Geospatial
- Source: https://source.coop/radiantearth/african-crops-tanzania-01
- Page: https://scigantic.com/archive/e600aa21-afcf-5762-92ec-351d4fb3e6b1
- Keywords: Earth Observation & Geospatial, satellite imagery, time series, TIFF, Azure Blob Storage

## About

Ground reference crop type labels for smallholder fields in Tanzania, collected by the Great African Food Company and published by Radiant Earth Foundation as machine learning training data, with matching Sentinel-2 imagery. Field staff used the Farmforce app to record one point inside each field together with village, region, plot area in acres, planting date and crop; harvest dates were estimated from FAO crop calendars. Radiant Earth drew a polygon within each field from the point, the recorded plot area and Sentinel-2 true- and false-color scenes plus Google basemap imagery, and dropped points that could belong to a neighboring farm, so polygons sample the field rather than cover it. The folder holds label GeoJSON tiles (ref_african_crops_tanzania_01_tile_*.geojson) and label/ rasters, an imagery/ tree with one subfolder per tile and per Sentinel-2 acquisition date at a five-day cadence through 2018, Tanzania_properties.csv describing the label fields, and Tanzania_Documentation.pdf on collection methods. Use it to train and test crop type classifiers for East African agriculture. Read with geopandas and rasterio. Licensed CC BY 4.0 (DataCite record for DOI 10.34911/rdnt.5vx40r); cite Great African Food Company (2019).

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/african-crops-01/tanzania/')[:10]
```

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

## Data structure

File types in sampled files: TIFF

Example file: `imagery/00/00_20180102/00_20180102_B01_10m.tif`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/e600aa21-afcf-5762-92ec-351d4fb3e6b1
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/e600aa21-afcf-5762-92ec-351d4fb3e6b1
- Over MCP: `get_schema_card` with id `e600aa21-afcf-5762-92ec-351d4fb3e6b1` 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)
- [TIFF datasets](https://scigantic.com/topics/tiff)
- [Time series datasets](https://scigantic.com/topics/time-series)
