A partnership between  H2i Balkans (Sarajevo, Bosnia and Herzegovina) and GISAT (Prague, Czech Republic) won the support of the UNDP Challenge Fund for a project entitled: “Computer Vision Flood Forecasting using Remotely Sensed Data”. The objective of the Challenge Fund is to facilitate the transfer of the know how and innovative solutions that addresses development challenges in Bosnia and Herzegovina (B&H), Georgia and Moldova and contribute to achievements of SDGs

The project solicits the latest technology from different fields: Remote Sensing to acquire Earth Observations (EO) data, Computer Vision to process the data and Machine Learning (ML) to develop models in order to relate meteorological and other EO data with flooding. The project addresses one of the most pressing problems B&H currently faces – increasingly frequent occurrence of floods. Combination of Czech and B&H expertise will be demonstrated on a real-world case of river Bregava, situated in the South-East of B&H.

The project is supported by Adriatic Sea Watershed Agency which furnishes in situ observations and provides socio-economic context for the application of the project outcomes. Bringing together advances in remote sensing, processing these data using machine learning and computer vision techniques, will result in accurate models of rainfall–runoff behaviours, which will help Water Agency and the Federal Hydrometeorological Institute with flood predictions and management. Additionally, the social, environmental and financial potential of the project is enormous.