Quality zones automatically identified in water distribution networks by applying data clustering methods to conductivity measurements. (1st December 2021)

• Record Type: Journal Article
• Authors: Mandel, Pierre; Wang, Yue; Parre, Anatole; Féliers, Cédric; Heim, Véronique
• Is Part Of: Water research. Volume 207(2021)
• Publication Date: 2021-12-01
• Subjects: Water distribution system -- Water origin detection -- Conductivity time-series -- OPTICS clustering -- Dynamic Time Warping -- Automatic cluster extraction method; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2021.117716
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: 4-year operational conductivity measurements from 215 probes were studied. Main characteristics of the network studied: 8500 km pipes, 4.6 M customers. Conductivity can be used to characterize water origin and water residence time. Mixing zones and tank-influenced zones can be isolated with the proposed method. Conductivity-based clusters offer a prior tool for contamination warning systems. Abstract: This paper presents a clustering study showing how conductivity measured every five minutes by 215 probes over four years can be used to determine specific quality zones for a large Water Distribution Network (WDN): 8500 km of pipes, 4.6 M customers. Conductivity time-series are compared using Dynamic Time Warping. Then, probes are ordered using a density-based method, and probe clusters are extracted automatically. The clusters are a sound representation of water quality in the WDN, both in terms of water origin and water residence time. More specifically, zones directly impacted by plants or by external water imports, mixing zones and zones influenced by tanks, can be isolated and analyzed. Globally, 82% of the probes were found to be clustered, consistent with expert knowledge on the WDN operation; 13% were unclassified; 3% were erroneously clustered; and 1% seemed to be reasonably clustered, without any physical understanding yet. Besides providing users with an increased understanding of water quality in WDNs, conductivity-based clusters offer an interesting prior tool for contamination warning systems. Graphical abstract: Image, graphical abstract