[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127376-en":3,"doc-seo-127376-105":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},127376,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Integrating dynamic features into machine learning models for predicting sewer network failures - a Random Forest approach","Sewer blockages and flooding continue to challenge water utilities, where teams often rely on labour-intensive and iterative detection methods such as CCTV inspections and jetting. Machine learning asset failure prediction offers a proactive alternative by ranking vulnerable pipe sections for targeted inspection and intervention. This study integrates sediment transport mechanics, derived from network hydraulic models, into a predictive Random Forest framework. Results show that dynamic sediment-related features capturing transport capacity and spatial variation substantially increase predictive performance.","Urban Water Journal  \nISSN: 1573-062X (Print) 1744-9006 (Online) Journal [homepage: ](homepage: www.tandfonline.com/journals/nurw20)[www.tandfonline.com/journals/nurw20](homepage: www.tandfonline.com/journals/nurw20)  \nIntegrating dynamic features into machine learning models for predicting sewer network failures: a Random Forest approach  \nOussama Aounali, Will Shepherd & Simon Tait  \nTo cite this article: Oussama Aounali, Will Shepherd & Simon Tait (21 Nov 2025): Integrating dynamic features into machine learning models for predicting sewer network failures: a Random Forest approach, Urban Water Journal, DOI: 10.1080/1573062X.2025.2589081  \nTo link to this article: [https://doi.org/10.1080/1573062X.2025.2589081](https://doi.org/10.1080/1573062X.2025.2589081)  \n© 2025 The Author(s) . Published by Informa UK Limited, trading as Taylor & Francis Group.  \n\n|  View supplementary material  |\n| --- |\n|  Published online: 21 Nov 2025. |\n|  Submit your article to this journal  |\n|  Article views: 71 |\n|  View related articles  |\n|  View Crossmark data |\n\nFull Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=nurw20](https://www.tandfonline.com/action/journalInformation?journalCode=nurw20)  \nRESEARCH ARTICLE     \nIntegrating dynamic features into machine learning models for predicting sewer network failures: a Random Forest approach  \nOussama Aounali , Will Shepherd  and Simon Tait   \nSchool of Mechanical, Aerospace and Civil Engineering, University of Sheffield, Sheffield, UK  \nABSTRACT  \nSewer blockages and flooding remain persistent challenges. Water utilities often deploy labourintensive, iteratrive approaches, such as repeated CCTV inspections and jetting, to detect and address these problems. Recently, machine learning (ML) based asset failure prediction has emerged as a cost-effective alternative, enabling proactive identification of vulnerable pipe sections that can then be the focus for inspection and intervention. Early ML-based predictive models primarily focused on non-dynamic factors, such as physical pipe attributes, while newer approaches have incorporated dynamic variables like rainfall and pipe flow, resulting in significant accuracy improvements. This study examines the integration of sediment transport mechanics, using network hydraulic model derived parameters, into a predictive Random Forest (RF) model. Results demonstrate that incorporating dynamic features representing sediment transport capacity and its spatial variation considerably enhances the RF model’s predictive power, offering a more reliable tool for identifying and managing blockages, and flooding in combined sewer networks.  \nARTICLE HISTORY  \nReceived 4 February 2025 Accepted 7 November 2025  \nKEYWORDS  \nSewer asset failures; riskbased maintenance; sediment mechanics; Random Forest classifier; predictive models  \nIntroduction  \nAddressing sewer failures, such as localised flooding or structural failure has traditionally been a reactive process, focusing on interventions after failures occurs. This approach is not only costly but also ineffective in preventing environmental damage and service disruptions, which can result in significant costs for water utilities and adverse effects on public health and the environment (Draude et al. 2019; Rosin et al. 2022) . As urbanisation and climate change exacerbate these challenges, there isan urgent need to develop more effective strategies for managing sewer failures.  \nSeveral factors commonly contribute to sewer failures, with pipe deterioration, environmental impacts, and system load variations among the most significant. Studies such as Jin and Mukherjee (2010) have highlighted issues like ageing infrastructure, root intrusions, and construction defects, often compounded by inadequate maintenance, as key causes of sewer system failures. Early work by Arthur, Crow, and Pedezert (2008) emphasized the vulnerability of combined sewer systems","cbCaioTDuOxK0SVw","https://ap.wps.com/l/cbCaioTDuOxK0SVw","pdf",2230234,1,17,"English","en",105,"# Abstract\n# Introduction\n## Reactive vs. proactive sewer failure management\n## Key drivers of sewer failures\n## Physical, environmental, and operational contributors\n## Hydraulic parameters and sediment transport","[{\"question\":\"Why is proactive prediction of sewer network failures important?\",\"answer\":\"Reactive interventions after failures are costly and can allow environmental damage and service disruption. Proactive prediction supports earlier identification of vulnerable pipe sections for targeted inspection and intervention.\"},{\"question\":\"How do dynamic features improve machine learning predictions in this study?\",\"answer\":\"The approach adds dynamic variables linked to sediment transport mechanics, represented through hydraulic-model-derived parameters. These features capture sediment transport capacity and spatial variation, improving Random Forest predictive power.\"},{\"question\":\"What role does the Random Forest model play?\",\"answer\":\"A predictive Random Forest framework is used to model sewer network failures. The study evaluates how integrating sediment-related dynamic features changes the model’s performance.\"}]","Integrating dynamic features into machine learning models for predicting sewer network failures - a Random Forest approach | PDF",1785938574,43,{"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},"integrating-dynamic-features-into-machine-learning-models-for-predicting-sewer-network-failures-a-random-forest-approach","",{"@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/integrating-dynamic-features-into-machine-learning-models-for-predicting-sewer-network-failures-a-random-forest-approach/127376/",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","2026-08-05",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 is proactive prediction of sewer network failures important?","Question",{"text":75,"@type":76},"Reactive interventions after failures are costly and can allow environmental damage and service disruption. Proactive prediction supports earlier identification of vulnerable pipe sections for targeted inspection and intervention.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do dynamic features improve machine learning predictions in this study?",{"text":80,"@type":76},"The approach adds dynamic variables linked to sediment transport mechanics, represented through hydraulic-model-derived parameters. These features capture sediment transport capacity and spatial variation, improving Random Forest predictive power.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does the Random Forest model play?",{"text":84,"@type":76},"A predictive Random Forest framework is used to model sewer network failures. The study evaluates how integrating sediment-related dynamic features changes the model’s performance.","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":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]