Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study
This study presents a comprehensive evaluation of 10 state of the art semi-supervised anomaly detection (AD) methods for leakage identification in water distribution networks (WDNs). The performances of the semi-supervised AD methods is evaluated on LeakDB, a benchmark consisting of independent leak...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-12-01
|
Series: | Machine Learning with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827023000543 |
_version_ | 1797405339830714368 |
---|---|
author | Hoese Michel Tornyeviadzi Hadi Mohammed Razak Seidu |
author_facet | Hoese Michel Tornyeviadzi Hadi Mohammed Razak Seidu |
author_sort | Hoese Michel Tornyeviadzi |
collection | DOAJ |
description | This study presents a comprehensive evaluation of 10 state of the art semi-supervised anomaly detection (AD) methods for leakage identification in water distribution networks (WDNs). The performances of the semi-supervised AD methods is evaluated on LeakDB, a benchmark consisting of independent leakage scenarios that also account for the various sources of uncertainties arising in WDNs. Three performance metrics (Fβ Measure, PR AUC Score, and Identification Lag Time) that collectively capture the different facets of leakage identification in WDNs is utilised to measure the efficacy of semi-supervised AD methods. Additionally, the TOPSIS MCDM tool supported with two weighting approaches is implemented to simultaneously consider all performance metrics in ranking the performance of semi-supervised AD methods. The results of this extensive comparative study shows that Local Outlier factor (LOF) is the overall best performing semi-supervised AD method on LeakDB. It is also evident that proximity based semi-supervised AD methods are superior to linear and probabilistic AD methods due to their ability to unearth leak events in the neighbourhood of normal operational data points. Finally, the impact of uncertainties on the performance of the semi-supervised AD models is discussed in addition to general recommendations on the usage of semi-supervised AD methods in leakage identification. |
first_indexed | 2024-03-09T03:09:27Z |
format | Article |
id | doaj.art-e56459947ea040baa2a3741a87c7f428 |
institution | Directory Open Access Journal |
issn | 2666-8270 |
language | English |
last_indexed | 2024-03-09T03:09:27Z |
publishDate | 2023-12-01 |
publisher | Elsevier |
record_format | Article |
series | Machine Learning with Applications |
spelling | doaj.art-e56459947ea040baa2a3741a87c7f4282023-12-04T05:24:27ZengElsevierMachine Learning with Applications2666-82702023-12-0114100501Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative studyHoese Michel Tornyeviadzi0Hadi Mohammed1Razak Seidu2Corresponding author.; Smart Water Lab, Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology, Ålesund, NorwaySmart Water Lab, Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology, Ålesund, NorwaySmart Water Lab, Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology, Ålesund, NorwayThis study presents a comprehensive evaluation of 10 state of the art semi-supervised anomaly detection (AD) methods for leakage identification in water distribution networks (WDNs). The performances of the semi-supervised AD methods is evaluated on LeakDB, a benchmark consisting of independent leakage scenarios that also account for the various sources of uncertainties arising in WDNs. Three performance metrics (Fβ Measure, PR AUC Score, and Identification Lag Time) that collectively capture the different facets of leakage identification in WDNs is utilised to measure the efficacy of semi-supervised AD methods. Additionally, the TOPSIS MCDM tool supported with two weighting approaches is implemented to simultaneously consider all performance metrics in ranking the performance of semi-supervised AD methods. The results of this extensive comparative study shows that Local Outlier factor (LOF) is the overall best performing semi-supervised AD method on LeakDB. It is also evident that proximity based semi-supervised AD methods are superior to linear and probabilistic AD methods due to their ability to unearth leak events in the neighbourhood of normal operational data points. Finally, the impact of uncertainties on the performance of the semi-supervised AD models is discussed in addition to general recommendations on the usage of semi-supervised AD methods in leakage identification.http://www.sciencedirect.com/science/article/pii/S2666827023000543Anomaly detectionLeakage detectionSemi-supervised learningWater distribution networks |
spellingShingle | Hoese Michel Tornyeviadzi Hadi Mohammed Razak Seidu Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study Machine Learning with Applications Anomaly detection Leakage detection Semi-supervised learning Water distribution networks |
title | Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study |
title_full | Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study |
title_fullStr | Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study |
title_full_unstemmed | Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study |
title_short | Semi-supervised anomaly detection methods for leakage identification in water distribution networks: A comparative study |
title_sort | semi supervised anomaly detection methods for leakage identification in water distribution networks a comparative study |
topic | Anomaly detection Leakage detection Semi-supervised learning Water distribution networks |
url | http://www.sciencedirect.com/science/article/pii/S2666827023000543 |
work_keys_str_mv | AT hoesemicheltornyeviadzi semisupervisedanomalydetectionmethodsforleakageidentificationinwaterdistributionnetworksacomparativestudy AT hadimohammed semisupervisedanomalydetectionmethodsforleakageidentificationinwaterdistributionnetworksacomparativestudy AT razakseidu semisupervisedanomalydetectionmethodsforleakageidentificationinwaterdistributionnetworksacomparativestudy |