The OECD.AI Policy Navigator

Our policy navigator is a living repository from more than 80 jurisdictions and organisations. Use the filters to browse initiatives and find what you are looking for.

Satellite-based system for waterlogging detection using artificial intelligence


Added by:   OECD analyst
Added on:   30 Sep 2026
Updated by:   OECD analyst
Updated on:   30 Sep 2026

A satellite-based AI system was developed for the public water management authority JP “Vode Vojvodine” to detect waterlogging and map risk areas across Vojvodina, helping them make faster and more informed decisions. The platform combines satellite images, weather data and soil information to identify where excess water may cause damage. It was created to reduce agricultural losses and support better planning, prevention and response to extreme weather conditions.

Name in original language

Satelitski sistem za detekciju vodoleži primenom veštačke inteligencije

Initiative overview

The initiative addresses the growing challenges caused by excess water and waterlogging in agricultural areas of Vojvodina, which often lead to crop losses, inefficient water management and increased operational costs for public institutions. Developed for the public water management authority JP “Vode Vojvodine”, the solution introduces satellite monitoring and artificial intelligence to support faster detection, mapping and analysis of waterlogged areas.

By replacing manual field monitoring with continuous digital observation, the initiative leverages the opportunity to modernise melioration system management and improve climate resilience. The main objective of the initiative is to enable more efficient management of drainage infrastructure through accurate and timely information. The system provides historical waterlogging maps, regional intensity analysis and an AI-based risk map that helps prioritise maintenance of canal networks and melioration activities.

As a result, the public authority can better direct resources to high-risk locations, reduce unnecessary field visits and improve decision-making processes, ultimately protecting agricultural production and public investments. In the future, the initiative is expected to evolve from a project-based solution into a continuously used digital service integrated into institutional workflows.

Through the Space Garden platform, the system already provides ongoing access to satellite-derived insights, climate indicators and soil information, allowing long-term monitoring and planning. Further institutionalisation may include expansion to additional water management regions and integration with other environmental monitoring tools.

Results, outcomes and impacts

The initiative delivered a fully operational satellite-based AI system for JP “Vode Vojvodine”, including historical waterlogging maps (10 m resolution), regional intensity analysis and a Vojvodina-wide risk map. Results were measured through satellite data validation, comparison with historical precipitation records and field observations.

The system reduces the need for manual monitoring and supports faster decision-making in melioration management. In the future, it is expected to improve prevention planning, reduce agricultural losses and expand towards broader climate-risk monitoring for additional users such as insurers and financial institutions.

Other relevant details

Challenges and lessons learned: The main challenge was limited historical waterlogging data, which required extensive manual analysis of satellite imagery to identify past events. Additional challenges involved balancing map visualisation between detailed insights and regional overview, as well as integrating datasets with different spatial resolutions, from 10 m satellite data to 1 km soil parameters. These issues were addressed through data harmonisation, interpolation techniques and improved visual heatmaps. A key lesson learned is that strong data infrastructure, flexible technical development and close collaboration with domain experts are essential for successful AI-driven public-sector solutions.

About the policy initiative


Category:

  • AI policy initiatives, programmes and projects

Initiative type:

  • AI use cases/projects in the public sector

Status:

  • Inactive – initiative complete

Start Year:

  • 2024

End Year:

  • 2025

OECD AI Principles:

—

Other relevant urls:

—