Multi-Source Dynamic Graph Learning for Compound-Flood Forecasting in Managed Coastal Systems
2026-08-03 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors study how flooding in coastal areas is affected by water conditions and management activities recorded at different monitoring stations. They point out that existing forecasting methods do well on average but may miss longer periods of very high water that are important for flood warnings. To fix this, the authors developed a new forecasting approach that adjusts predictions using information from multiple stations while keeping local forecasts stable. Their method better predicts these longer high-water events without losing accuracy for regular conditions, helping with flood alerts and water management.
compound floodingcoastal systemshydrometeorological datamulti-source forecastingtemporal dependencieserror metricstime series alignmentwater-managementhigh-water plateausearly warning systems
Authors
Liangjun You, Min Wu, Orlando Woods, Dongsheng Luo
Abstract
Compound flooding in managed coastal systems is influenced by hydrological conditions and water-management activity observed across multiple monitoring stations. Current forecasting models can capture temporal dependencies with low average errors, but global error metrics may conceal poor reproduction of prolonged high-water plateaus that are relevant to flood early warning. Because hydrometeorological and operational signals are distributed across heterogeneous gages, single-site records do not fully represent high-water dynamics. Nevertheless, unconstrained fusion of cross-site signals can degrade the stability of local temporal forecasts. This work proposes an anchored forecasting framework that incorporates cross-site information through state- and lead-dependent bounded residual corrections. A multi-source regime representation constructed from hydrometeorological and operational observations adaptively calibrates inter-site relationships and correction scales, enabling targeted cross-site adjustment while preserving the local temporal forecast as a stable anchor. Beyond conventional global error statistics, we evaluate event-scale high-water characteristics through the temporal alignment of forecasted and observed high-water processes. Experiments demonstrate that selectively integrating multi-station dynamic conditions improves the prediction reliability of sustained high-water plateaus while maintaining high accuracy during routine hydrological conditions, supporting flood early warning and water-management decision support.