# Dalberg Data Insights Uganda Crop Classification: field crop type, yield and pest labels with Sentinel-2 time series, 2017 (Radiant Earth MLHub)

## Facts

- Provider: Dalberg Data Insights; Radiant Earth Foundation
- License: CC-BY-4.0 (https://api.datacite.org/dois/10.34911/rdnt.eii04x)
- Format: TIFF (in sampled files)
- Stored at: Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/african-crops-01/uganda
- Access: public, readable without an account
- DOI: https://doi.org/10.34911/rdnt.eii04x
- Category: Earth Observation & Geospatial
- Source: https://source.coop/radiantearth/african-crops-uganda-01
- Page: https://scigantic.com/archive/df2b935c-eb72-5d6d-a870-a6ec193b3de0
- Keywords: Earth Observation & Geospatial, satellite imagery, time series, TIFF, Azure Blob Storage

## About

Field survey labels for crop classification in Uganda collected by Dalberg Data Insights and published by Radiant Earth Foundation, with a Sentinel-2 image time series for each label tile (acquisitions from January 2017 at a ten-day cadence, bands B01 to B12, B8A and a CLD cloud layer resampled to 10 m). Surveyors sampled 1.5 x 1.5 m quadrants within fields and recorded, per quadrant, the crop type and variety (indigenous or improved), plant counts, maize cob or sorghum ear counts, whether plants showed disease or fall armyworm damage and how many were affected; field-level attributes include village, subcounty and district, grain moisture, grain and stem weight, yield in kg per hectare and harvest index. That makes it useful both for crop type mapping and for yield and pest-damage modeling of maize and sorghum. The folder holds label GeoJSON tiles (ref_african_crops_uganda_01_tile_*.geojson) and label/ rasters, an imagery/ tree with one subfolder per tile and acquisition date, Uganda_properties.csv defining every property, and Uganda_Documentation.pdf on survey methods. Read with geopandas and rasterio. Licensed CC BY 4.0 (DataCite record for DOI 10.34911/rdnt.eii04x); cite Dalberg Data Insights, Uganda Crop Classification.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/african-crops-01/uganda/')[: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_20170105/00_20170105_B01_10m.tif`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/df2b935c-eb72-5d6d-a870-a6ec193b3de0
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/df2b935c-eb72-5d6d-a870-a6ec193b3de0
- Over MCP: `get_schema_card` with id `df2b935c-eb72-5d6d-a870-a6ec193b3de0` 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)
