Exploiting River Network Topology for Flood Forecasting with Graph Neural Networks

Nikolas Kirschstein, Yixuan Sun

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: graph neural networks, adjacency relation, river network, flood forecasting

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: investigating the benefit of relating river gauging stations via graph neural networks for flood forecasting

Abstract: Climate change exacerbates riverine floods, which occur with higher frequency and intensity than ever. The much-needed forecasting systems typically rely on accurate river discharge predictions. To this end, the SOTA data-driven approaches treat forecasting at spatially distributed gauge stations as isolated problems, even within the same river network. However, incorporating the known river network topology into the prediction model has the potential to leverage the adjacency relationship between gauges. Thus, we model river discharge for a network of gauging stations with a GNN, and compare the forecasting performance achieved by different adjacency definitions. Our results show that the model fails to benefit from the river network topology information, regardless of the number of layers and, thus, propagation distance. The learned edge weights correlate with neither of the static definitions and exhibit no regular pattern. Furthermore, a worst-case analysis reveals that the GNN struggles to predict sudden discharge spikes. This work may serve as a justification for the SOTA treating gauges independently and suggests that more improvement potential lies in anticipating spikes.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1991