Learning Surrogate Rainfall-driven Inundation Models with Few Data

TL;DR

This paper introduces a novel surrogate flood inundation model combining ensemble Gaussian processes with deep learning, achieving rapid and accurate flood predictions with minimal data, suitable for climate and hazard assessments.

Contribution

It presents a new hybrid modeling approach that effectively leverages limited data to produce fast, accurate flood hazard predictions using deep learning initialized with ensemble Gaussian processes.

Findings

Achieved over 0.96 R-squared in flood depth predictions.

Median relative error in flood depth estimates is about 1%.

Runtime per event is approximately 0.006 seconds.

Abstract

Flood hazard assessment demands fast and accurate predictions. Hydrodynamic models are detailed but computationally intensive, making them impractical for quantifying uncertainty or identifying extremes. In contrast, machine learning surrogates can be rapid, but training on scarce simulated or observed extreme data can also be ineffective. This work demonstrates the development of an effective surrogate model for flood hazard prediction by initializing deep learning (ResNet-18) with ensemble-approximated Conditional Gaussian Processes (EnsCGP) and finalizing it with a bias correction. The proposed methodology couples EnsCGP with a ResNet-18 architecture to estimate flood depth and uses ensemble optimal estimation for bias correction. The surrogate model was trained and evaluated using rainfall data from Daymet and hydrodynamic simulations from LISFLOOD-FP, spanning the period from 1981 to 2019. The training involved using data up to a certain year and testing on the subsequent year, iteratively progressing through the dataset. This process required approximately 100 training iterations and extensive data. Inundation depths are estimated rapidly at runtime (approximately 0.006 seconds per event). Results over multiple years in the current climate over Chicago demonstrate an average R-squared greater than 0.96, with median relative errors in flood depth estimates of about 1 percent.