Join the GeoAI Challenge in 2026 (fifth edition), a competition aimed at providing solutions for collaboratively addressing real-world geospatial problems by applying artificial intelligence (AI)/machine learning (ML). Through this platform, participants will attempt to address the UN Sustainable Development Goals (SDGs) related problems using real-world data. In addition, participants will acquire hands-on experience in AI/ML in areas relevant to solving SDGs and compete for prizes, recognition, and certificates.
Ongoing challenge
GeoAI Aquaculture Pond Identification Challenge by FAO and ITU
Aquaculture ponds are used to farm fish and shrimp in controlled water environments. They are easier to manage and more productive than open-water fishing. But to monitor them effectively, we first need to know where they are. Satellite imagery offers a reliable way to map these ponds across large areas, providing up-to-date information that supports water management, environmental monitoring, and policy decisions, especially in regions where ground-level data is hard to come by.
Your goal is to build a machine learning model that predicts whether a given location is an aquaculture pond or another type of land cover, using features derived from satellite data. Each location represents a 10m × 10m patch of ground, so your model needs to be precise.
Challenge timeline
08 June 2026Start- 07 August 2026Enrolments close
- 16 August 2026Close
- 17 August 2026Reveal
Completed challenge
Reaching new heights with GeoFM
Producing accurate Digital Surface Models (DSM) and Digital Terrain Models (DTM) with ground cover information at a global scale remains a major challenge. Traditionally, these datasets rely on expensive airborne LiDAR surveys, which are not available everywhere. To tackle this issue, for the first time ever, the International Telecommunication Union (ITU) and AI for Good partners with ESA Φ-lab Challenges to present a new GeoAI Challenge. The joint “Reaching new heights with GeoFM” Challenge, marks an important step toward creating a global mapping of surface heights and land‑cover classes using only open‑access satellite imagery.
Reaching new heights with GeoFM Timeline
- February – April 2026Curation phase
- April – June 2026Competition phase
- July 2026Evaluation phase
Everything happens somewhere
Sky
Ground
Water + below surface level
Related sessions
25 February 2026
•14:00 - 15:30
EST - New York
CST - Beijing
PST - Los Angeles
AWST - Perth, Australia
19 March 2026
•14:00 - 15:30
EST - New York
CST - Beijing
PST - Los Angeles
AWST - Perth, Australia
30 March 2026
•14:00 - 15:00
EST - New York
CST - Beijing
PST - Los Angeles
AWST - Perth, Australia
8 April 2026
•14:00 - 15:00
EST - New York
CST - Beijing
PST - Los Angeles
AWST - Perth, Australia
Benefits
Crowdsourcing multiple solutions for high-impact problems that could improve real production AI/ML systems
Increasing awareness about the problem domain and your work either in research or business
Access to a growing and highly skilled talent pool of AI researchers, students, and professionals interested in the same problems as your group for further collaborations or hiring
Technical partners
12 October 2026
