Зображення обкладинки

Discriminator‐Guided Generative Adversarial Networks for Urban Flood Prediction

Збережено в:
Опубліковано в::Water Resources Research vol. 61, no. 11 (Nov 1, 2025)
Автор: Li, Zhufeng
Інші автори: Fu, Zeyu, Li, Qian, Fu, Guangtao
Опубліковано:
John Wiley & Sons, Inc.
Предмети:
Dams
Flood management
Deep learning
Floods
Discriminators
Rainfall
Water depth
Neural networks
Generative adversarial networks
Computer applications
Spatial discrimination
Flood control
Design rainfall
Flood forecasting
Precipitation
Predictions
Spatial resolution
Structure-function relationships
Decision making
Flood predictions
Flood models
Environmental
Онлайн доступ:Citation/Abstract
Full Text
Full Text - PDF
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
Короткий огляд:Flood modeling is crucial in flood management as it can provide early warnings and support informed decision‐making on mitigation and adaptation strategies. However, it remains challenging to provide accurate flood predictions in real time using hydrodynamic flood models due to high computational demands. This study presents a new discriminator‐guided Generative Adversarial Neural Networks (GANs) model for two‐dimensional, high‐resolution urban flood prediction. Compared with the traditional GANs, the role of the discriminator is re‐defined by modifying its structure and loss function, enabling pixel‐wise discrimination based on errors, thereby better meeting the requirements of high‐resolution flood prediction. The proposed model is tested on the case study of Exeter, which covers an area of 27 km2 with a spatial resolution of 2 m, compared with the baseline models of Pix2Pix and U‐Net. The proposed model can accurately predict the water depths across historical and design rainfall events, achieving an average root mean square error of 0.044 m and Critical Success Index of 0.754, demonstrating the generalization capability on unseen rainfall events. The proposed model significantly improves computational efficiency and offers a viable solution for spatiotemporal flood prediction in real‐time, providing informed decision‐making for urban flood management.
ISSN:0043-1397
1944-7973
DOI:10.1029/2025WR040510
Джерело:ABI/INFORM Global