# Central Asia Crop Type Polygons (Uzbekistan and Tajikistan, Aral Sea Basin)

## Facts

- Provider: Remelgado, Zaitov, Kenjabaev et al. (University of Halle, iDiv)
- License: CC-BY-4.0 (https://radiantearth.blob.core.windows.net/mlhub/idiv-asia-crop-type/README.md)
- Format: JSON (in sampled files)
- Stored at: Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/idiv-asia-crop-type
- Access: public, readable without an account
- DOI: https://doi.org/10.6084/m9.figshare.12047478.v2
- Category: Earth Observation & Geospatial
- Source: https://doi.org/10.6084/m9.figshare.12047478.v2
- Page: https://scigantic.com/archive/5cfe2ba6-e46a-5d6a-9638-5d39a7400792
- Keywords: Earth Observation & Geospatial, satellite imagery, time series, JSON, Azure Blob Storage

## About

Field-validated crop type reference polygons for land cover classification in the Aral Sea Basin, Central Asia, where irrigated agriculture drives water use. The authors collected 8,196 samples between 2015 and 2018, 213 in 2011 and 26 in 2008; 97.7% of the polygons are in Uzbekistan (Fergana Valley, Khorezm and other irrigated districts) and the rest in Tajikistan. Labels cover 40 crop types and are dominated by cotton (40%) and winter wheat (25%), with rice, alfalfa, maize, orchards, vineyards and double cropping classes. Polygons were checked against expert knowledge and Landsat and Sentinel-2 time series using open-source workflows so later campaigns stay consistent. Measured 2026-11-15: five files, about 30 MB in total, holding CAWa_cropType.zip (the shapefiles), a labels GeoJSON, the STAC collection and a PDF data description. Load the labels with geopandas and pair them with Sentinel-2 or Landsat imagery for supervised crop mapping. Released under CC BY 4.0; cite Remelgado et al. (2020), figshare, doi:10.6084/m9.figshare.12047478.v2, and the companion Scientific Data descriptor.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/idiv-asia-crop-type/')[:10]
```

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

## Data structure

File types in sampled files: JSON

Example file: `.source/metadata.json`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/5cfe2ba6-e46a-5d6a-9638-5d39a7400792
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/5cfe2ba6-e46a-5d6a-9638-5d39a7400792
- Over MCP: `get_schema_card` with id `5cfe2ba6-e46a-5d6a-9638-5d39a7400792` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [JSON datasets](https://scigantic.com/topics/json)
- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [Time series datasets](https://scigantic.com/topics/time-series)
