Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecasting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Hongjun, Chen, Jiyuan, Zheng, Yinqiang, Song, Xuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912271800729600
author Wang, Hongjun
Chen, Jiyuan
Zheng, Yinqiang
Song, Xuan
author_facet Wang, Hongjun
Chen, Jiyuan
Zheng, Yinqiang
Song, Xuan
contents Climate change-driven floods demand advanced forecasting models, yet Graph Neural Networks (GNNs) underutilize river network topology due to tree-like structures causing over-squashing from high node resistance distances. This study identifies this limitation and introduces a reachability-based graph transformation to densify topological connections, reducing resistance distances. Empirical tests show transformed-GNNs outperform EA-LSTM in extreme flood prediction, achieving 24-h water level accuracy equivalent to EA-LSTM's 14-h forecasts - a 71% improvement in long-term predictive horizon. The dense graph retains flow dynamics across hierarchical river branches, enabling GNNs to capture distal node interactions critical for rare flood events. This topological innovation bridges the gap between river network structure and GNN modeling, offering a scalable framework for early warning systems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecasting
Wang, Hongjun
Chen, Jiyuan
Zheng, Yinqiang
Song, Xuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Climate change-driven floods demand advanced forecasting models, yet Graph Neural Networks (GNNs) underutilize river network topology due to tree-like structures causing over-squashing from high node resistance distances. This study identifies this limitation and introduces a reachability-based graph transformation to densify topological connections, reducing resistance distances. Empirical tests show transformed-GNNs outperform EA-LSTM in extreme flood prediction, achieving 24-h water level accuracy equivalent to EA-LSTM's 14-h forecasts - a 71% improvement in long-term predictive horizon. The dense graph retains flow dynamics across hierarchical river branches, enabling GNNs to capture distal node interactions critical for rare flood events. This topological innovation bridges the gap between river network structure and GNN modeling, offering a scalable framework for early warning systems.
title Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecasting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2410.05536