Large-scale flood modeling and forecasting with FloodCast

Abstract

Large-scale hydrodynamic models generally rely on fixed-resolution spatial grids and model parameters as well as incurring a high computational cost. This limits their ability to accurately forecast flood crests and issue time-critical hazard warnings. In this work, we build a fast, stable, accurate, resolution-invariant, and geometry-adaptative flood modeling and forecasting framework that can perform at large scales, namely FloodCast. The framework comprises two main modules: multi-satellite observation and hydrodynamic modeling. In the multi-satellite observation module, a real-time unsupervised change detection method and a rainfall processing and analysis tool are proposed to harness the full potential of multi-satellite observations in large-scale flood prediction. In the hydrodynamic modeling module, a geometry-adaptive physics-informed neural solver (GeoPINS) is introduced, benefiting from the absence of a requirement for training data in physics-informed neural networks and featuring a fast, accurate, and resolution-invariant architecture with Fourier neural operators. GeoPINS demonstrates impressive performance on popular PDEs across regular and irregular domains. Building upon GeoPINS, we propose a sequence-to-sequence GeoPINS model to handle long-term temporal series and extensive spatial domains in large-scale flood modeling. Next, we establish a benchmark dataset in the 2022 Pakistan flood to assess various flood prediction methods. Finally, we validate the model in three dimensions - flood inundation range, depth, and transferability of spatiotemporal downscaling. Traditional hydrodynamics and sequence-to-sequence GeoPINS exhibit exceptional agreement during high water levels, while comparative assessments with SAR-based flood depth data show that sequence-to-sequence GeoPINS outperforms traditional hydrodynamics, with smaller prediction errors.

Figures (16)

• Figure 1: Overall of flood modeling and forecasting (FloodCast) system.
• Figure 2: Overall of unsupervised change detection.
• Figure 3: The full architecture of Geometry-adaptive physics-informed neural solver.
• Figure 4: Train on a low spatial-temporal resolution (first column) directly infer on a spatial-temporal resolution $256 \times 100$ by GeoPINS with FD (second column) and GeoPINS with FFT PS (third column). (a) 1-D convection equations on regular domain ($\beta$=20). (b) 1-D convection equations on regular domain ($\beta$=30). (c) 1-D convection equations on regular domain ($\beta$=40)
• Figure 5: The physical domain (upper left) and reference domain (lower left) for 2-D Navier-Stokes equations. Velocity (the first row) and pressure (the second row) contours of CFD benchmakrk, Regular PINN, PhyGeoNet, and GeoPINS. All methods are fully trained at $\nu=0.01$.