Dalberg Data Insights Uganda Crop Classification: field crop type, yield and pest labels with Sentinel-2 time series, 2017 (Radiant Earth MLHub)
- Provider
- Dalberg Data Insights; Radiant Earth Foundation
- License
- CC-BY-4.0 (source)
- Format
- TIFF (in sampled files)
- Stored at
- Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/african-crops-01/uganda
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.34911/rdnt.eii04x
- Category
- Earth Observation & Geospatial
- Source
- https://source.coop/radiantearth/african-crops-uganda-01
About this dataset
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.
How to access this dataset in 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
Files
Example file: imagery/00/00_20170105/00_20170105_B01_10m.tif
Analyze this dataset without downloading it
On Scigantic, Dalberg Data Insights Uganda Crop Classification: field crop type, yield and pest labels with Sentinel-2 time series, 2017 (Radiant Earth MLHub) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Earth Observation & Geospatial datasets
- Overture Maps - Roads Dataset (PMTiles) - Riyadh, Saudi Arabia
- Satellite - Sea surface temperature - Level 3 - Single sensor - 6 day - Day and night time
- Euclid Quick Release 1 (Q1)
- USGS Watershed Boundary Dataset
- Sample images
- GridNet-HD: UAV LiDAR and Image Fusion Dataset for 3D Semantic Segmentation of Power Line Infrastructure (HEIG-VD)
- NASA HEASARC: NICER Mission Data Archive
- LGND Clay v1.5 Sentinel-2