An evaluation of deep learning models for predicting water depth evolution in urban floods

TL;DR

This paper evaluates various deep learning models for predicting high-resolution water depth in urban floods, aiming to provide faster, accurate forecasts as an alternative to computationally intensive hydrodynamic models.

Contribution

It compares multiple deep learning models trained on simulated flood data to assess their accuracy and generalization in urban flood prediction scenarios.

Findings

Deep learning models generally outperform other methods in error reduction.

Models are more accurate for water depths greater than 0.5 meters.

Performance declines on complex rainfall events and unseen catchments.

Abstract

In this technical report we compare different deep learning models for prediction of water depth rasters at high spatial resolution. Efficient, accurate, and fast methods for water depth prediction are nowadays important as urban floods are increasing due to higher rainfall intensity caused by climate change, expansion of cities and changes in land use. While hydrodynamic models models can provide reliable forecasts by simulating water depth at every location of a catchment, they also have a high computational burden which jeopardizes their application to real-time prediction in large urban areas at high spatial resolution. Here, we propose to address this issue by using data-driven techniques. Specifically, we evaluate deep learning models which are trained to reproduce the data simulated by the CADDIES cellular-automata flood model, providing flood forecasts that can occur at different future time horizons. The advantage of using such models is that they can learn the underlying physical phenomena a priori, preventing manual parameter setting and computational burden. We perform experiments on a dataset consisting of two catchments areas within Switzerland with 18 simpler, short rainfall patterns and 4 long, more complex ones. Our results show that the deep learning models present in general lower errors compared to the other methods, especially for water depths $>0.5m$. However, when testing on more complex rainfall events or unseen catchment areas, the deep models do not show benefits over the simpler ones.