[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126335-en":3,"doc-seo-126335-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":11,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126335,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Evaluating Yangtze River Delta Urban Agglomeration - Flood Risk Assessment Using a Hybrid Method of Automated Machine Learning and Analytic Hierarchy Process","Rapid urbanization increases the need for scientifically grounded flood-disaster risk assessment, yet selecting optimal machine-learning models and analyzing spatial–temporal patterns across urban agglomerations remains difficult. This study builds an H–E–V–R index system for Yangtze River Delta Urban Agglomeration by combining hazard, exposure, vulnerability, and resilience factors. Automated machine learning and analytic hierarchy process are integrated to generate a comprehensive flood risk model. Results show CatBoost yields the best categorical identification performance, elevation is the most important hazard factor, and overall flood risk rises heterogeneously from 1990 to 2020, supporting prevention and sustainable development.","Nat. Hazards Earth Syst. Sci., 25, 3087–3108, 2025 [https://doi.org/10.5194/nhess-25-3087-2025](https://doi.org/10.5194/nhess-25-3087-2025)[ ](https://doi.org/10.5194/nhess-25-3087-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nEvaluating Yangtze River Delta Urban Agglomeration flood risk using a hybrid method of automated machine learning and analytic hierarchy process  \nYu Gao 1,2 , Haipeng Lu 1,2 , Yaru Zhang 1,2 , Hengxu Jin 1,2 , Shuai Wu3 , Yixuan Gao 1,2 , and Shuliang Zhang 1,2,4  \n1 Key Laboratory of VGE of the Ministry of Education, Nanjing Normal University, Nanjing 210023, China  \n2Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China  \n3Lianyungang Real Estate Registry, Lianyungang 222006, China  \n4 State Key Laboratory of Climate System Prediction and Risk Management, Nanjing Normal University, Nanjing 210023, China  \nCorrespondence: Shuliang Zhang ([zhangshuliang@njnu.edu.cn](zhangshuliang@njnu.edu.cn))  \nReceived: 31 July 2024 – Discussion started: 16 September 2024  \nRevised: 18 May 2025 – Accepted: 15 June 2025 – Published: 5 September 2025  \nAbstract. With rapid urbanization, the scientific assessment of disaster risk caused by flooding events has become an essential task for disaster prevention and mitigation. However, adaptively selecting optimal machine learning (ML) models for flood risk assessment and further conducting spatial and temporal analyses of flood risk characteristics in urban agglomerations remain challenging. This study establishes an H–E–V–R risk assessment index system that integrates hazard, exposure, vulnerability, and resilience based on the factors influencing flood risk in the Yangtze River Delta Urban Agglomeration (YRDUA) . Utilizing automated machine learning (AutoML) and the analytic hierarchy process (AHP), a comprehensive flood risk assessment model is constructed. Results indicate that, among the different assessment models, the accuracy, precision, F1 score, and kappa coefficient of the categorical boosting (CatBoost) model for flooded point identification are the highest. Among the flood hazard factors, elevation ranks highest in importance, with a contribution rate of up to 68.55 % . The spatial distribution of flood risk in the study area from 1990 to 2020 is heterogeneous, with an overall increasing risk trend. This study is of great significance, advancing disaster prevention, mitigation, and sustainable development in the YRDUA.  \n1 Introduction  \nUnder global climate change and accelerated urbanization, China has been experiencing pervasive flooding ever more frequently (Tang et al., 2024) . Floods threaten people's lives, hinder social development, and cause huge economic losses in China (Anon, 2021; Echendu, 2020; Milanesi et al., 2015) . Flood formation has been exacerbated by climate change and urbanization, leading to increased frequency, extent, and intensity of urban flooding and impacting urban flood risk (Mahmoud and Gan, 2018; Khadka et al., 2023; Scott et al., 2023; Seemuangngam and Lin, 2024) . Modern human society is faced with the possibility of serious flood hazards and associated challenges, and in addition to post-disaster emergency management, the scientific assessment of disaster risks arising from flood events has gradually become a crucial aspect of preventing and mitigating disasters.  \nCurrently, most research in the field of flooding focuses on the flood risks of individual cities (Wang et al., 2021, 2023b; Guan et al., 2024) . However, in recent years, the frequency and intensity of urban flooding in China have increased dramatically, and individual cities are no longer able to independently mitigate the risks arising from floods. Studies indicate that China's flood risk management needs to be transformed from the scale of isolated individual cities to the scale of urban agglomerations, conducted in a regionally coordinated manner (Moral","cbCaieYUAK5TZTgb","https://ap.wps.com/l/cbCaieYUAK5TZTgb","pdf",8507481,1,22,"English","en",105,"# Introduction\n## Flood risk assessment challenges\n## Need for urban agglomeration scale studies\n## Current assessment methods\n## Data-driven approaches and machine learning","[{\"question\":\"What index system does the study use for flood risk assessment?\",\"answer\":\"It establishes an H–E–V–R index system covering hazard, exposure, vulnerability, and resilience based on key factors influencing flood risk in the Yangtze River Delta Urban Agglomeration.\"},{\"question\":\"How are automated machine learning and AHP combined in the model?\",\"answer\":\"Automated machine learning is used to construct the flood risk assessment model, while the analytic hierarchy process is integrated to support the overall framework for comprehensive evaluation.\"},{\"question\":\"Which model and factor show the strongest results and importance?\",\"answer\":\"CatBoost achieves the highest accuracy, precision, F1 score, and kappa for flooded-point identification, and elevation ranks highest in hazard importance with a contribution rate up to 68.55%.\"}]","Evaluating Yangtze River Delta Urban Agglomeration - Flood Risk Assessment Using a Hybrid Method of Automated Machine Learning and Analytic Hierarchy Process | PDF",1785904523,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"evaluating-yangtze-river-delta-urban-agglomeration-flood-risk-assessment-using-a-hybrid-method-of-automated-machine-learning-and-analytic-hierarchy-process","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluating-yangtze-river-delta-urban-agglomeration-flood-risk-assessment-using-a-hybrid-method-of-automated-machine-learning-and-analytic-hierarchy-process/126335/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What index system does the study use for flood risk assessment?","Question",{"text":76,"@type":77},"It establishes an H–E–V–R index system covering hazard, exposure, vulnerability, and resilience based on key factors influencing flood risk in the Yangtze River Delta Urban Agglomeration.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are automated machine learning and AHP combined in the model?",{"text":81,"@type":77},"Automated machine learning is used to construct the flood risk assessment model, while the analytic hierarchy process is integrated to support the overall framework for comprehensive evaluation.",{"name":83,"@type":74,"acceptedAnswer":84},"Which model and factor show the strongest results and importance?",{"text":85,"@type":77},"CatBoost achieves the highest accuracy, precision, F1 score, and kappa for flooded-point identification, and elevation ranks highest in hazard importance with a contribution rate up to 68.55%.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]