[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124421-en":3,"doc-seo-124421-105":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},124421,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Risk-Based Water Pipe Failure Prediction Through Machine Learning and Hydraulic Models","Failures in Water Transmission Lines (WTLs) can trigger major disruptions, costly repairs, and wide-area impacts, motivating proactive prediction-based maintenance. Existing risk identification approaches often struggle with limited failure data, particularly for large-diameter pipes, reducing prediction accuracy. This study introduces a hybrid framework that combines tree-based machine learning and hydraulic modelling using 48 South Korean networks (2008–2023), incorporating pipe attributes, environmental and operational factors, and failure history. XGBoost with class weighting achieves the strongest classification performance, while hydraulic simulation quantifies isolation-driven supply shortages and secondary damages. An economic prioritization balances repair cost with risk reduction, supporting cost-effective rehabilitation planning, efficient resource allocation, and reduced water loss.","Risk-Based Water Pipe Failure Prediction Through Machine Learning and Hydraulic Models  \nTaegon Ko1, Raziyeh Farmani2, Edward Keedwell3, Ramiz Beig Zali4  \n1PhD Candidate, Centre for Water Systems, Department of Engineering, University of Exeter, Exeter EX1 4QF, U.K; Email: [tk447@exeter.ac.uk](tk447@exeter.ac.uk) (Corresponding author), ORCID: Taegon Ko (0009-0000-4696-0507)  \n([orcid.org](orcid.org))  \n2Professor, Centre for Water Systems, Department of Engineering, University of Exeter, Exeter EX1 4QF, U.K; [Email: R.Farmani@exeter.ac.uk](Email: R.Farmani@exeter.ac.uk), ORCID: Raziyeh Farmani (0000-0002-9818-1879) ([orcid.org](orcid.org))  \n3Professor, Department of Computer Science, University of Exeter, Exeter EX1 4QF , U.K; Email:  \n[E.C.Keedwell@exeter.ac.uk](E.C.Keedwell@exeter.ac.uk), ORCID: Edward Keedwell (0000-0003-3650-6487) ([orcid.org](orcid.org))  \n4PhD Candidate, Centre for Water Systems, Department of Engineering, University of Exeter, Exeter EX1 4QF, U.K; Email: [rb815@exeter.ac.uk](rb815@exeter.ac.uk), ORCID: Ramiz Beig Zali (0000-0003-2814-9838) ([orcid.org](orcid.org))  \nAbstract  \nFailures in Water Transmission Lines (WTLs) can cause severe disruptions, high repair costs, and extensive damage to surrounding areas. To mitigate these risks, there is a growing interest in proactive management through predictive methods. Traditional methods for identifying high-risk pipelines are often constrained by the scarcity of available data, especially for largediameter pipes, making accurate failure prediction challenging. This study proposes a hybrid approach combining machine learning techniques with hydraulic modelling to improve the accuracy of pipe failure risk predictions. Using data from 48 water transmission networks in South Korea, including pipe intrinsic properties, environmental conditions, operational factors, and failure history from 2008 to 2023 , the study applied tree-based machine learning models (Random Forest, XGBoost, and CatBoost) along with various data sampling techniques to predict the probability of pipe failure. XGBoost with class weighting showed the best performance across key evaluation metrics, including F1-score, F2-score, AUC-ROC and AUC-PR. A hydraulic model was used to assess the impact of pipe isolation, quantifying water  \nsupply shortages and secondary damages. An economic analysis was conducted to prioritize pipeline rehabilitation, balancing the cost of repair with risk reduction. The results demonstrate a cost-effective approach to risk-based maintenance planning, enabling utilities to allocate resources efficiently for pipeline rehabilitation while minimizing disruption and water loss.  \nKeywords: Pipe failure prediction, Hydraulic impact analysis, Water transmission line risk assessment, Machine learning, Cost-effective maintenance planning  \nIntroduction  \nWater transmission lines (WTLs) are critical infrastructure that transport a large volume of water to communities and industries. Failures in these systems not only disrupt daily life and industrial processes but also result in financial burdens, including emergency repair costs, compensation to customers, and damage to surrounding infrastructure. Therefore, maintaining the reliability of these systems is crucial. To mitigate these risks, water utilities focus on identifying pipes that require timely rehabilitation as part of a proactive management strategy. Besides timely rehabilitation, regular condition assessments are crucial for maximizing the lifespan of existing, well-maintained pipes, ensuring that unnecessary rehabilitation is avoided. These assessments ensure cost-effective management and continuously enhance the resilience of the pipelines. However, because WTLs are deeply buried, physical inspections are challenging and limited, and failure analyses often rely on historical failure data. There is less historical failure data available for WTLs since they fail less frequently than mains with smaller diameters (","cbCaiphU9tEGmqrp","https://ap.wps.com/l/cbCaiphU9tEGmqrp","pdf",1178472,1,47,"English","en",105,"# Abstract\n# Introduction\n# Literature review","[{\"question\":\"Why is predicting water transmission line failures difficult?\",\"answer\":\"Failure prediction is challenging because WTLs have limited historical failure data and the influencing factors are complex, involving intrinsic pipe properties, environmental conditions, and operational influences.\"},{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"The study uses a hybrid approach that combines tree-based machine learning models with hydraulic modelling to both estimate the probability of pipe failure and evaluate the consequences of pipe isolation.\"},{\"question\":\"Which model performed best and how were hydraulic impacts used?\",\"answer\":\"XGBoost with class weighting delivered the best overall performance across evaluation metrics. A hydraulic model then assessed isolation impacts by quantifying water supply shortages and secondary damages, supporting risk-based rehabilitation prioritization.\"}]","Risk-Based Water Pipe Failure Prediction Through Machine Learning and Hydraulic Models | PDF",1785822182,118,{"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},"risk-based-water-pipe-failure-prediction-through-machine-learning-and-hydraulic-models","",{"@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/risk-based-water-pipe-failure-prediction-through-machine-learning-and-hydraulic-models/124421/",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","2026-08-04",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 predicting water transmission line failures difficult?","Question",{"text":75,"@type":76},"Failure prediction is challenging because WTLs have limited historical failure data and the influencing factors are complex, involving intrinsic pipe properties, environmental conditions, and operational influences.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the core idea of the proposed method?",{"text":80,"@type":76},"The study uses a hybrid approach that combines tree-based machine learning models with hydraulic modelling to both estimate the probability of pipe failure and evaluate the consequences of pipe isolation.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performed best and how were hydraulic impacts used?",{"text":84,"@type":76},"XGBoost with class weighting delivered the best overall performance across evaluation metrics. A hydraulic model then assessed isolation impacts by quantifying water supply shortages and secondary damages, supporting risk-based rehabilitation prioritization.","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"]