Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling

TL;DR

This paper introduces a deep learning approach for physics-aware downsampling of terrain maps, enabling scalable flood modeling by reducing computational costs while preserving accuracy.

Contribution

It presents a novel neural network method that optimizes coarse terrain representations for flood prediction, improving scalability without sacrificing detail accuracy.

Findings

Significant reduction in computational cost achieved.

Maintains high accuracy in flood simulation.

Provides a dataset and implementation for reproducibility.

Abstract

Background: Floods are the most common natural disaster in the world, affecting the lives of hundreds of millions. Flood forecasting is therefore a vitally important endeavor, typically achieved using physical water flow simulations, which rely on accurate terrain elevation maps. However, such simulations, based on solving partial differential equations, are computationally prohibitive on a large scale. This scalability issue is commonly alleviated using a coarse grid representation of the elevation map, though this representation may distort crucial terrain details, leading to significant inaccuracies in the simulation. Contributions: We train a deep neural network to perform physics-informed downsampling of the terrain map: we optimize the coarse grid representation of the terrain maps, so that the flood prediction will match the fine grid solution. For the learning process to succeed, we configure a dataset specifically for this task. We demonstrate that with this method, it is possible to achieve a significant reduction in computational cost, while maintaining an accurate solution. A reference implementation accompanies the paper as well as documentation and code for dataset reproduction.