# CV4A Kenya Crop Type Competition Dataset: Sentinel-2 time series with PlantVillage field labels, Kenya 2019 (Radiant Earth Foundation)

## Facts

- Provider: Radiant Earth Foundation and PlantVillage
- License: CC-BY-SA-4.0 (https://api.datacite.org/dois/10.34911/rdnt.dw605x)
- Format: TIFF (in sampled files)
- Stored at: Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/kenya-crop-challenge
- Access: public, readable without an account
- DOI: https://doi.org/10.34911/rdnt.dw605x
- Category: Earth Observation & Geospatial
- Source: https://source.coop/radiantearth/african-crops-kenya-02
- Page: https://scigantic.com/archive/021e7cd7-d27d-539b-bfbd-3b27a9cc2f78
- Keywords: Earth Observation & Geospatial, satellite imagery, time series, TIFF, Azure Blob Storage

## About

The crop type training dataset of the CV4A (Computer Vision for Agriculture) Kenya competition, published by Radiant Earth Foundation: Sentinel-2 multispectral image time series over smallholder farms in Kenya during the 2019 growing season, paired with per-pixel crop labels and field identifiers. Ground data were collected by PlantVillage with its mobile app, walking points around each field with basemap imagery as a guide; Radiant Earth then quality-controlled the polygons against Sentinel-2 and Google basemap imagery, removing overlapping fields with conflicting labels, fixing invalid shapes and dropping fields too small for a Sentinel-2 pixel. Seven classes follow the FAO crop list: maize, cassava, common bean, and the intercrops maize and common bean, maize and cassava, maize and soybean, and cassava and common bean. The data/ folder holds four tiles (0 to 3), each with _label.tif and _field_id.tif rasters and one subfolder per acquisition date (20190606 through the season) of Sentinel-2 band GeoTIFFs (B01 to B12, B8A, and a CLD cloud probability layer); FieldIds.csv lists the train/test fields and Documentation.pdf describes collection methods. Read with rasterio or rioxarray. Licensed CC BY-SA 4.0 (DataCite record for DOI 10.34911/rdnt.dw605x); cite Radiant Earth Foundation (2020), CV4A Competition Kenya Crop Type Dataset.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/kenya-crop-challenge/')[: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: `data/0/0_field_id.tif`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/021e7cd7-d27d-539b-bfbd-3b27a9cc2f78
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/021e7cd7-d27d-539b-bfbd-3b27a9cc2f78
- Over MCP: `get_schema_card` with id `021e7cd7-d27d-539b-bfbd-3b27a9cc2f78` 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)
