[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128501-en":3,"doc-seo-128501-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},128501,687207017582,"Himbo","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Event-based decision support algorithm for real-time flood forecasting in urban drainage systems using machine learning modelling","Urban flooding threatens cities worldwide and drives major socio-economic losses. Conventional real-time flood forecasting models depend on continuous time-series data and often show reduced accuracy, particularly for lead times beyond 2 hours. This study introduces an event-based decision support algorithm using event identification, event-based dataset generation, and a real-time decision-tree flowchart powered by machine learning. Results on a real-world case study indicate improved water-level rise forecasting for longer lead times (2–3 hours). The framework cuts RMSE by 50%, boosts forecasting accuracy by 50%, and improves normalized Nash–Sutcliffe error by 20%, reducing false alarms and missed floods while strengthening emergency response.","Environmental Modelling and Software 167 (2023) 105772  \nContents lists available at ScienceDirect  \nEnvironmental Modelling and Software  \njournal [homepage:](homepage: www.elsevier.com/locate/envsoft)[ www.elsevier.com/locate/envsoft](homepage: www.elsevier.com/locate/envsoft)  \n| Event-based decision support algorithm for real-time flood forecasting in urban drainage systems using machine learning modelling\u003Cbr>Farzad Piadeha, Kourosh Behzadiana, b, *, Albert S. Chenc, Luiza C. Campos b, Joseph P. Rizzutoa, Zoran Kapeland\u003Cbr>a School of Computing and Engineering, University of West London, St Mary’s Rd, London, W5 5RF, UK\u003Cbr>b Department of Civil, Environmental and Geomatic Engineering, University College London, Gower St, London, WC1E 6BT, UK c Centre for Water Systems, Faculty of Environment, Science and Economy, University of Exeter, Exeter, EX4 4QF, UK\u003Cbr>d Department of Water Management, Faculty of Civil Engineering and Geosciences, Delft University of Technology (TU Delft), Delft, Netherlands |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Handling Editor: Daniel P Ames |  | Urban flooding is a major problem for cities around the world, with significant socio-economic consequences. Conventional real-time flood forecasting models rely on continuous time-series data and often have limited accuracy, especially for longer lead times than 2 hrs. This study proposes a novel event-based decision support algorithm for real-time flood forecasting using event-based data identification, event-based dataset generation, and a real-time decision tree flowchart using machine learning models. The results of applying the framework toa real-world case study demonstrate higher accuracy in forecasting water level rise, especially for longer lead times (e.g., 2–3 hrs), compared to traditional models. The proposed framework reduces root mean square error by 50%, increases accuracy of flood forecasting by 50%, and improves normalised Nash–Sutcliffe error by 20%. The proposed event-based dataset framework can significantly enhance the accuracy of flood forecasting, reducing the occurrences of both false alarms and flood missing and improving emergency response systems. |\n| Keywords:\u003Cbr>Event identification\u003Cbr>Machine learning\u003Cbr>Online platform\u003Cbr>Real-time flood forecasting\u003Cbr>Urban drainage systems |  |  |\n\nSoftware and data availability  \n- Programming language: MATLAB 2021b using Machine learning and deep learning toolbox.  \n- Hardware requirement: Any computer with windows 10 and newer, any intel or AMD x86-64 processor, 4 GB minimum RAM, 8 GB minimum storage, no specific graphics card.  \n- Written code: 72 KB Modular code contains main file with 5 function files, available [at github.com/FarzadPiadeh21452390/Event-based](at github.com/FarzadPiadeh21452390/Event-based)platform.git  \n- Dataset: Ruislip water level data, Heathrow, Iver Heath, and RAF Northolt rainfall data (London, UK) used in this study. Real-time data are available and can be directly extracted by using an application programming interface (API) provided by the UK Environment Agency up to the last 28 days. Long-term historic data can also be available as csv file format in “[environment.data.gov.uk/flood](environment.data.gov.uk/flood)monitoring” free of charge for research purposes by the UK Environment Agency upon request.  \n1. Introduction  \nUrban flooding is one of the most devastating natural disasters, and its impacts on economic, population, and property loss can be exacerbated by climate change (Xie et al., 2017). However, the use of real-time urban flood forecasting (RTUFF) models can help mitigate these impacts effectively by providing early warning for emergency response, early action, and contingency planning (Ahmed et al., 2021). Urban flooding can be described as a temporary overland flow in urban areas, including pluvial, fluvial, coastal, flash, groundwater, and urban drainage systems (UDS) flooding (Hamil, 2011). UDS flooding","cbCail6b3b7Y4uRF","https://ap.wps.com/l/cbCail6b3b7Y4uRF","pdf",13706248,1,19,"English","en",105,"# Introduction\n## Urban flooding and limitations of conventional forecasting\n## Real-time urban flood forecasting background\n# Proposed event-based decision support algorithm\n## Event identification and event-based dataset generation\n## Real-time decision-tree flowchart with machine learning\n# Results and performance improvements\n## Case study comparison for longer lead times\n## Error reduction and accuracy gains\n# Software and data availability\n## Programming language and hardware requirements\n## Code repository and datasets\n## Real-time and long-term data sources","[{\"question\":\"Why do conventional real-time flood forecasting models underperform for longer lead times?\",\"answer\":\"They rely on continuous time-series inputs and often provide limited accuracy when lead times extend beyond about 2 hours.\"},{\"question\":\"What are the core components of the proposed event-based decision support algorithm?\",\"answer\":\"It combines event-based data identification, event-based dataset generation, and a real-time decision-tree flowchart using machine learning models.\"},{\"question\":\"How much did the proposed framework improve forecasting accuracy?\",\"answer\":\"It reduced RMSE by 50%, increased forecasting accuracy by 50%, and improved normalized Nash–Sutcliffe error by 20%, especially for 2–3 hour lead times.\"}]","Event-based decision support algorithm for real-time flood forecasting in urban drainage systems using machine learning modelling | PDF",1786001419,48,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"event-based-decision-support-algorithm-for-real-time-flood-forecasting-in-urban-drainage-systems-using-machine-learning-modelling","",{"@graph":36,"@context":85},[37,54,68],{"@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/event-based-decision-support-algorithm-for-real-time-flood-forecasting-in-urban-drainage-systems-using-machine-learning-modelling/128501/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-06",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do conventional real-time flood forecasting models underperform for longer lead times?","Question",{"text":75,"@type":76},"They rely on continuous time-series inputs and often provide limited accuracy when lead times extend beyond about 2 hours.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the core components of the proposed event-based decision support algorithm?",{"text":80,"@type":76},"It combines event-based data identification, event-based dataset generation, and a real-time decision-tree flowchart using machine learning models.",{"name":82,"@type":73,"acceptedAnswer":83},"How much did the proposed framework improve forecasting accuracy?",{"text":84,"@type":76},"It reduced RMSE by 50%, increased forecasting accuracy by 50%, and improved normalized Nash–Sutcliffe error by 20%, especially for 2–3 hour lead times.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]