Accelerating Urban Flood Inundation Simulation Under Spatio‐Temporally Varying Rainstorms Using ConvLSTM Deep Learning Model

Abstract Urban floods induced by rainstorms can lead to severe losses of lives and property, making rapid flood prediction essential for effective disaster prevention and mitigation. However, traditional deep learning (DL) models often overlook the spatial heterogeneity of rainstorms and lack interp...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaoxing Liao, Zhaoli Wang, Haijun Yu, Weizhi Gao, Zhaoyang Zeng, Xuefang Li, Chengguang Lai
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2025WR040433
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Urban floods induced by rainstorms can lead to severe losses of lives and property, making rapid flood prediction essential for effective disaster prevention and mitigation. However, traditional deep learning (DL) models often overlook the spatial heterogeneity of rainstorms and lack interpretability. Here, we propose an end‐to‐end rapid prediction method for urban flood inundation incorporating spatiotemporal varying rainstorms using a Convolutional Long Short‐Term Memory Network (ConvLSTM) DL model. We compare the performance of the proposed method with that of a 3D Convolutional Neural Network (3D CNN) model and introduce the spatial visualization technique Grad‐CAM to interpret the rainstorms contributions to flood predictions. Results demonstrate that: (a) Compared to the physics‐based model, the proposed ConvLSTM model achieves satisfactory accuracy in predicting flood inundation evolution under spatio‐temporal varying rainstorms, with an average Pearson correlation coefficient (PCC) of 0.958 and a mean absolute error (MAE) of 0.021 m, successfully capturing the locations of observed inundation points under actual rainstorm conditions. (b) The ConvLSTM model can rapidly predict urban rainstorm inundation process in just 2 s for a study area of 74 km2, which is 170 times more efficient than a physics‐based model. (c) The interpretability of the ConvLSTM model for urban flood prediction can be enhanced through Grad‐CAM, revealing the model naturally focuses on local or upstream rainfall concentration areas most responsible for inundation, aligning well with hydrological understanding. Overall, the ConvLSTM model serves as a powerful surrogate for rapid urban flood simulation, providing an important reference for real‐time flood early warning and mitigation.
ISSN:0043-1397
1944-7973