Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

EA-MiniGrid-Bench: A High-Resolution Spatial Benchmark Dataset for Machine Learning in East African Energy Planning

Domain:

environment and energygeospatial

Record type:

dataset
Creator:
AkaOla
Publisher:
Zenodo
Host:avatar
EA-MiniGrid-Bench is an open, ML-ready tabular benchmark dataset for solar mini-grid viability assessment across Rwanda, Kenya, Uganda, and Tanzania. It comprises 175,253 validated grid-cell records at 2–3 km resolution, encoding mean Global Horizontal Irradiance (GHI), population count, and road proximity, enriched with country and two levels of administrative labels and per-cell coordinates. Derived from the Global Solar Atlas, WorldPop 2025, OpenStreetMap, and open administrative boundaries via a reproducible Python pipeline. Released with the complete processing and experiment code.

Visit

doi.orgzenodo.org

Tags

mini-grid, rural electrification, East Africa, solar energy, geospatial, benchmark dataset, machine learning.

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode