Flood risk prediction with quantum-classical machine learning

Current flood risk prediction relies on the learning of historical datasets from hydrological monitoring, such as river water level, weather forecast and rainfall volume, to build a reliable flood model. We propose a hybrid quantum-classical machine learning to forecast flood events with smaller historical dataset, higher forecast accuracy and faster learning time.

This quantum use case is developed with Open Quantum Institute (OQI), aligned with their A1 objective, i.e. accelerating the exploration of use cases. The other team members are Mohamad Amin bin Hamid and Siti Aqilah Muhamad Rasat.