2019 Mali Crop Type Training Data (NASA Harvest, Sentinel-2)

Provider
Nakalembe, Ouedraogo, Diarra and Kuzimbu (University of Maryland, NASA Harvest)
License
CC-BY-4.0 (source)
Format
JSON (in sampled files)
Stored at
Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/umd-mali-crop-type
Access
Free and public. No account with the data provider is needed.
DOI
10.34911/rdnt.tgz68o
Category
Earth Observation & Geospatial
Source
https://doi.org/10.34911/rdnt.tgz68o

About 2019 Mali Crop Type Training Data (NASA Harvest, Sentinel-2)

Crop type ground reference for Mali in the 2019 growing season from the NASA Harvest team at the University of Maryland, collected with an ODK smartphone app and matched to Sentinel-2 time series. Classes are maize, millet, rice and sorghum, the main staple cereals of the Sahel. Field polygons were rasterised onto the Sentinel-2 10 m grid, so each label raster lines up with a stack of Sentinel-2 L2A observations through the season for training pixel or field classifiers. Funding came from Lutheran World Relief, the Bill & Melinda Gates Foundation and NASA Harvest. Measured 2026-11-15: 17,628 files (0.48 GB): 17,589 Sentinel-2 band GeoTIFFs under imagery/, 34 label rasters under labels/, labels.json, STAC JSON and a PDF description. Read with rasterio and pair dates with the per-tile labels. Released under CC BY 4.0; cite Nakalembe et al. (2021), 2019 Mali Crop Type Training Data for Machine Learning, Radiant MLHub, doi:10.34911/rdnt.tgz68o.

How to access 2019 Mali Crop Type Training Data (NASA Harvest, Sentinel-2) in Python

import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/umd-mali-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

Files

Example file: .source/metadata.json

Analyze this dataset without downloading it

On Scigantic, 2019 Mali Crop Type Training Data (NASA Harvest, Sentinel-2) 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