A rapid flood inundation modelling framework using deep learning with spatial reduction and reconstruction. (September 2021)

• Record Type: Journal Article
• Authors: Zhou, Yuerong; Wu, Wenyan; Nathan, Rory; Wang, Quan J.
• Is Part Of: Environmental modelling & software. Volume 143(2021)
• Publication Date: 2021-09
• Subjects: Flood inundation modelling -- Deep learning -- Long short-term memory -- Spatial reduction; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2021.105112
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Traditional approaches to inundation modelling are computationally intensive and thus not well suited to assessing the uncertainty involved in estimating flood inundation surfaces for planning, design and forecasting purposes. In this study, a rapid flood inundation modelling framework is developed, consisting of a novel spatial reduction and reconstruction (SRR) approach and a deep learning (DL) modelling component. The SRR approach is developed to reduce computational cost by identifying representative locations of inundation surfaces where water levels are simulated using DL models, and to efficiently reconstruct inundation surfaces based on simulated water level information. The DL model includes a built-in input selection layer to simplify the model development process, and a Long Short-Term Memory layer for time series modelling. The accuracy and efficiency of the SRR-DL framework is assessed by application to a real-world river system where the inundation of over 3 million grid cells can be simulated in 4 s. Highlights: A deep-learning-based framework is developed to model flood inundation time series. A spatial reduction and reconstruction method is used to improve model efficiency. A built-in input selection layer is included to simplify model development process. The framework detects inundation with over 99% accuracy. Flood inundation surface of over 3 million grid cells can be simulated in 4s.