Cluster Analysis and Predictive Modeling of Urban Water Distribution System Leaks with Socioeconomic and Engineering Factors

Qing Shuang (), Rui Ting Zhao () and Erik Porse ()
Additional contact information
Qing Shuang: Beijing Jiaotong University
Rui Ting Zhao: Beijing Jiaotong University
Erik Porse: California State University

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2024, vol. 38, issue 1, No 20, 385-400

Abstract: Abstract Water distribution network (WDN) failures can disrupt operations and cause economic damage. Although leakage has been widely discussed, few studies have integrated spatial clusters with engineering, environmental, and socioeconomic factors simultaneously. This study proposes an approach to explore the role of socioeconomic factors in understanding leak risks. Using a unique data set of more than 4,000 reported leak events within the City of Los Angeles (2010–2013), the analysis (1) assesses the effectiveness of including socioeconomic factors with engineering factors in explaining observed leaks, (2) identifies spatial clusters of leaks, and (3) develops a predictive model with machine learning to identify spatial areas with high risks of failure. Results indicate that distinct clusters of leaks are evident, accounting for 20–30% of all leaks in the study area in a given year. Multivariate regression modeling showed that geography, socioeconomic, and engineering factors are statistically significant in predicting leaks. A predictive model with machine learning was developed, identifying key factors. The model had accuracy rates of 93.29% and 92.45% for interpolation and extrapolation prediction scenarios, respectively. The approach demonstrates the potential value of incorporating socioeconomic indicators into the models for WDN rehabilitation. Moreover, the approach demonstrates how municipal leak loss mitigation programs can consider a broad set of predictive factors to optimize investments.

Keywords: Water distribution network; Leakage cluster; Machine learning; Urban water management (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-023-03676-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:38:y:2024:i:1:d:10.1007_s11269-023-03676-w

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-023-03676-w

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().