Zhili Li , Zhiwei Zhou , Hao Wang , Xing Li , Xiaoyu Shi , Jiayi Xiao , Zhiyu Yang , Mingzhuang Sun , Xiaolong Li , Haifeng Jia
{"title":"Artificial intelligence-incorporated prediction for urban flooding processes in the past 20 years: A critical review","authors":"Zhili Li , Zhiwei Zhou , Hao Wang , Xing Li , Xiaoyu Shi , Jiayi Xiao , Zhiyu Yang , Mingzhuang Sun , Xiaolong Li , Haifeng Jia","doi":"10.1016/j.envsoft.2025.106525","DOIUrl":null,"url":null,"abstract":"<div><div>Urban flood forecasting is crucial for timely public warnings and effective flood management. Traditional mechanistic models face challenges such as high computational costs and limited real-time capabilities. Recent advancements in Artificial Intelligence (AI), including machine learning (ML), deep learning (DL), and large language models (LLMs), address these limitations by improving data handling, feature engineering, and forecasting accuracy. This review examines AI applications and evolution in urban flood forecasting, and features about commonly applied models such as convolutional neural networks (CNN), random forest (RF), long short-term memory (LSTM), and support vector machines (SVM). A comprehensive analysis compares various AI algorithms based on input parameters, output variables, forecasting lead time, and prediction accuracy. Key input parameters (\"Rainfall,\" \"Water depth,\" \"Elevation\") and output variables (\"Inundation depth,\" \"Inundation area,\" \"Flow\") were identified. Future research directions aim to enhance AI-driven forecasting precision for improved emergency response.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106525"},"PeriodicalIF":4.6000,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Modelling & Software","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1364815225002099","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Urban flood forecasting is crucial for timely public warnings and effective flood management. Traditional mechanistic models face challenges such as high computational costs and limited real-time capabilities. Recent advancements in Artificial Intelligence (AI), including machine learning (ML), deep learning (DL), and large language models (LLMs), address these limitations by improving data handling, feature engineering, and forecasting accuracy. This review examines AI applications and evolution in urban flood forecasting, and features about commonly applied models such as convolutional neural networks (CNN), random forest (RF), long short-term memory (LSTM), and support vector machines (SVM). A comprehensive analysis compares various AI algorithms based on input parameters, output variables, forecasting lead time, and prediction accuracy. Key input parameters ("Rainfall," "Water depth," "Elevation") and output variables ("Inundation depth," "Inundation area," "Flow") were identified. Future research directions aim to enhance AI-driven forecasting precision for improved emergency response.
期刊介绍:
Environmental Modelling & Software publishes contributions, in the form of research articles, reviews and short communications, on recent advances in environmental modelling and/or software. The aim is to improve our capacity to represent, understand, predict or manage the behaviour of environmental systems at all practical scales, and to communicate those improvements to a wide scientific and professional audience.