Eyes on the Ground: Smallholder Crop Photos with Damage and Phenology Labels (Kenya)
- Provider
- Waithaka, Kramer, Hufkens, Kivuva and Mansabdar (ACRE Africa, IFPRI, Lacuna Fund)
- License
- CC-BY-SA-4.0 (source)
- Format
- JSON (in sampled files)
- Stored at
- Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/koen_lacuna_fund
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.34911/rdnt.1bs2jw
- Category
- Earth Observation & Geospatial
- Source
- https://doi.org/10.34911/rdnt.1bs2jw
About this dataset
Georeferenced smartphone photographs of smallholder maize and other crop fields taken repeatedly by farmers across 8 counties in Kenya, collected through the Picture Based Insurance framework by ACRE Africa, the International Food Policy Research Institute (IFPRI) and the Lacuna Fund, with the CGIAR PIM programme. About 28,000 curated images carry manual labels for growth stage, damage type and damage extent, plus machine-learning labels for drought probability and extent, sowing, vegetative, flowering and maturity phases, and weed, drought and nutrient-deficit disturbance. Field locations are anonymised to regional bounding boxes; ancillary point extractions give Sentinel-2 reflectance for vegetation indices, ARC and TAMSAT rainfall estimates and ERA5 climate variables. Measured 2026-11-15: more than 40,000 files (at least 3 GB listed), mostly per-image zip archives and STAC item JSON under EotG_data_final/ (EotG_images/, ancillary_data/, catalog.json), plus a tarball of the full release and PDF documentation. Browse it with pystac. Released under CC BY-SA 4.0; cite Waithaka et al. (2022), Radiant MLHub, doi:10.34911/rdnt.1bs2jw.
How to access this dataset in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/koen_lacuna_fund/')[: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, Eyes on the Ground: Smallholder Crop Photos with Damage and Phenology Labels (Kenya) 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
- California Protected Areas Database
- AgriFieldNet India: Crop Type Labels for Smallholder Fields with Sentinel-2 Imagery
- STAC-GeoParquet of Sentinel 2 level 2a
- Met Office Global and Regional Ensemble Prediction System - UK (MOGREPS-UK) on a 30-day rolling archive
- CMIP6 GCMs downscaled using WRF
- ArcticDEM
- GHS-BUILT-H R2023A: Global Average Net Building Height (ANBH) Grid (JRC GHSL)
- GOES-18 Satellite Imagery