Great African Food Company Tanzania Ground Reference Crop Type Dataset with Sentinel-2 time series, 2018 (Radiant Earth MLHub)

Provider
Great African Food Company; 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/tanzania
Access
Free and public. No account with the data provider is needed.
DOI
10.34911/rdnt.5vx40r
Category
Earth Observation & Geospatial
Source
https://source.coop/radiantearth/african-crops-tanzania-01

About this dataset

Ground reference crop type labels for smallholder fields in Tanzania, collected by the Great African Food Company and published by Radiant Earth Foundation as machine learning training data, with matching Sentinel-2 imagery. Field staff used the Farmforce app to record one point inside each field together with village, region, plot area in acres, planting date and crop; harvest dates were estimated from FAO crop calendars. Radiant Earth drew a polygon within each field from the point, the recorded plot area and Sentinel-2 true- and false-color scenes plus Google basemap imagery, and dropped points that could belong to a neighboring farm, so polygons sample the field rather than cover it. The folder holds label GeoJSON tiles (ref_african_crops_tanzania_01_tile_*.geojson) and label/ rasters, an imagery/ tree with one subfolder per tile and per Sentinel-2 acquisition date at a five-day cadence through 2018, Tanzania_properties.csv describing the label fields, and Tanzania_Documentation.pdf on collection methods. Use it to train and test crop type classifiers for East African agriculture. Read with geopandas and rasterio. Licensed CC BY 4.0 (DataCite record for DOI 10.34911/rdnt.5vx40r); cite Great African Food Company (2019).

How to access this dataset in Python

import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/african-crops-01/tanzania/')[: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_20180102/00_20180102_B01_10m.tif

Analyze this dataset without downloading it

On Scigantic, Great African Food Company Tanzania Ground Reference Crop Type Dataset with Sentinel-2 time series, 2018 (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