Smallholder Cashew Plantations in Benin (Pleiades-derived labels with Sentinel-2)
- Provider
- Jin, Lin, Weigl, Obarowski and Hale (TechnoServe)
- License
- CC-BY-4.0 (source)
- Format
- JSON (in sampled files)
- Stored at
- Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/technoserve-cashew-benin
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.34911/rdnt.hfv20i
- Category
- Earth Observation & Geospatial
- Source
- https://doi.org/10.34911/rdnt.hfv20i
About this dataset
Pixel labels for cashew plantations over a 120 square kilometre area in central Benin, produced by TechnoServe's BeninCaju programme. Each pixel is classed as well-managed plantation, poorly-managed plantation, no plantation or another land cover class; labels come from field boundaries walked with handheld GPS and then corrected on Airbus Pleiades very high resolution imagery. The labels are paired with a Sentinel-2 L2A time series of the same area so that models can learn cashew canopy and management signals from 10 m multispectral data, relevant to tree crop mapping and yield programmes in West Africa. Measured 2026-11-15: 915 files (2.3 GB): 910 Sentinel-2 band GeoTIFFs under imagery/, one label raster and GeoJSON under labels/, STAC JSON and two PDF documents. Read with rasterio; torchgeo has a BeninSmallHolderCashews loader. Released under CC BY 4.0; cite Jin et al. (2021), Smallholder Cashew Plantations in Benin, Radiant MLHub, doi:10.34911/rdnt.hfv20i.
How to access this dataset in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/technoserve-cashew-benin/')[: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, Smallholder Cashew Plantations in Benin (Pleiades-derived labels with 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
- SEN2NEON: Sentinel-2 to NEON Hyperspectral Multispectral Super-Resolution Benchmark
- NUVIEW - Multi-State Geospatial Data
- MISR Level 1B2 Ellipsoid Data V004
- NREL WIND Toolkit: Southeast Asia wind resource data v3 (2007-2021) in HDF5 format
- Sentinel-1 Monthly Smoothed Backscatter Mosaics with uncertainty, VV/VH, western United States, 2022-2026, from OPERA RTC-S1 (Quadrature Earth, Source Cooperative)
- OPERA Land Surface Disturbance Annual from Harmonized Landsat Sentinel-2 product (Version 1)
- GDELT-SA
- MAN TruckScenes