中国防汛抗旱2024，Vol.34Issue(2)：16-22,7.DOI:10.16867/j.issn.1673-9264.2024022
基于深度学习和水动力模型的洪水演进快速模拟方法
Rapid simulation of flood routing using deep learning and hydrodynamic model
摘要
Abstract
The rapid simulation and early warning of flood disasters are crucial for flood prevention and mitigation.However,the current simulation efficiency of urban flood models based on physical mechanisms remains low.In this study,a deep learning model based on convolutional neural network(CNN)is constructed by combining flood inundation data generated by hydrodynamic model and deep learning techniques to rapidly simulate urban flood routing.The results show that the developed CNN model can effectively simulate the flood inundation,with a peak water depth prediction error within 8%,and a good performance in simulating the inundation extent.The CNN model demonstrates a significantly higher efficiency in flood inundation simulation,achieving approximately 400 times faster computation while maintaining comparable accuracy to hydrodynamic models.This study can provide valuable insights for rapid simulation of urban flood inundation,early warning and forecasting of flood disasters,and the development of digital twin basins.关键词
洪水淹没/水动力模型/深度学习/快速模拟Key words
flood routing/hydrodynamic model/deep learning/rapid simulation分类
信息技术与安全科学引用本文复制引用
廖耀星,高玮志,张轩,赖成光,王兆礼..基于深度学习和水动力模型的洪水演进快速模拟方法[J].中国防汛抗旱,2024,34(2):16-22,7.基金项目
国家自然科学基金项目(52379010)和广东省基础与应用基础研究基金项目(2023B1515020087、2022A1515010019). （52379010）
