Flood Prediction with Graph Neural Networks (Papers Track)

Arnold N Kazadi (Rice University); James Doss-Gollin (Rice University); Antonia Sebastian (UNC Chapel Hill); Arlei Silva (Rice University)

Paper PDF Slides PDF Recorded Talk NeurIPS 2022 Poster Topia Link Cite
Extreme Weather


Climate change is increasing the frequency of flooding around the world. As a consequence, there is a growing demand for effective flood prediction. Machine learning is a promising alternative to hydrodynamic models for flood prediction. However, existing approaches focus on capturing either the spatial or temporal flood patterns using CNNs or RNNs, respectively. In this work, we propose FloodGNN, which is a graph neural network (GNN) for flood prediction. Compared to existing approaches, FloodGNN (i) employs a graph-based model (GNN); (ii) operates on both spatial and temporal dimensions; and (iii) processes the water flow velocities as vector features, instead of scalar features. Experiments show that FloodGNN achieves promising results, outperforming an RNN-based baseline.

Recorded Talk (direct link)