Geo-Hub — Rwanda's Satellite-and-AI Platform for National Crop Monitoring
Rwanda
Rwanda launched Geo-Hub, a machine-learning platform combining satellite imagery and field data to map crop area and climate stress, piloted …
Slovenia · Ljubljana · See the Slovenia profile · See the Ljubljana profile
Evidence: Observational / pre–post Top 7% 87/100 · Ask Evidence Copilot about this practice
Slovenia's agricultural payments agency checks EU farm-subsidy compliance for over a million parcels every two weeks using Sentinel-2 satellite time series and machine-learning classification, finding about 98% automatically compliant.
Slovenia's ARSKTRP (Agency for Agricultural Markets and Rural Development) implements the EU Common Agricultural Policy's 'checks by monitoring' approach using free Copernicus Sentinel-2 satellite imagery, processed through the Sentinel Hub API with European Space Agency support, to verify farmers' subsidy-claim parcels against declared land use and crop type — replacing most on-site inspection visits.
The system runs cloud-filtering, spectral-index and time-series analysis roughly every two weeks through the growing season. Seven analytical markers — including homogeneity, minimal agricultural activity, mowing detection, bare-soil presence and a machine-learning crop classifier — feed a 'traffic light' verdict per parcel.
In the 2022 claim year the system evaluated more than one million individual parcels: about 98% were automatically confirmed compliant (green), with roughly 1% referred to human expert judgement or an on-site visit (yellow/red).
The European Court of Auditors' 2020 special report found adoption of 'checks by monitoring' uneven across the EU — only 15 of 66 paying agencies used Copernicus data for any scheme in 2019 — making Slovenia's subsequent national rollout a notable case of moving from partial pilot to comprehensive, recurring, whole-country coverage.
National / regional programmes
Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.
Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.
Where this practice's information was retrieved from, and when.
Rwanda
Rwanda launched Geo-Hub, a machine-learning platform combining satellite imagery and field data to map crop area and climate stress, piloted …
Mongolia
Mongolia's National Statistics Office piloted satellite-and-drone machine-learning models in Arkhangai province, identifying large livestock with 81.6% accuracy and traditional ger …
United States of America
UC San Diego's ALERTCalifornia network of 1,200+ AI-monitored cameras helped CAL FIRE respond to roughly 3,600 wildfire incidents in 2025; …
Türkiye
Within three days of the 2023 Kahramanmaraş earthquakes, Microsoft's AI for Good Lab used deep learning on satellite imagery to …
Open full copilot Grounded in cited practices — always check the sources.