A Deep U-Net Framework for Flood Hazard Mapping Using Hydraulic Simulations of the Wupper Catchment

TL;DR

This paper introduces a deep learning surrogate model based on U-Net architecture for rapid flood hazard mapping, offering a computationally efficient alternative to traditional hydraulic simulations.

Contribution

It develops and optimizes a deep U-Net framework to accurately predict flood water levels, reducing computational costs in flood hazard modeling.

Findings

The surrogate model achieves comparable accuracy to hydraulic simulations.

The framework significantly reduces computation time.

Validated on Wupper catchment data in Germany.

Abstract

The increasing frequency and severity of global flood events highlights the need for the development of rapid and reliable flood prediction tools. This process traditionally relies on computationally expensive hydraulic simulations. This research presents a prediction tool by developing a deep-learning based surrogate model to accurately and efficiently predict the maximum water level across a grid. This was achieved by conducting a series of experiments to optimize a U-Net architecture, patch generation, and data handling for approximating a hydraulic model. This research demonstrates that a deep learning surrogate model can serve as a computationally efficient alternative to traditional hydraulic simulations. The framework was tested using hydraulic simulations of the Wupper catchment in the North-Rhein Westphalia region (Germany), obtaining comparable results.