ABSTRACT
Understanding leakage is an important challenge within the water sector to minimise waste, energy use and carbon emissions. Every Water Distribution Network (WDN) has leakage, usually approximated as Minimum Night Flow (MNF) for each District Metered Area (DMA). However, not all DMAs have instruments to monitor leakage directly, or the main dynamic factors that contribute to it. Therefore, this article will estimate the leakage of a DMA by using the recorded features of its pipes, making use of readily available asset data collected routinely by water companies. This article interprets this problem as a feature construction task and uses a multi-objective multi-gene strongly typed genetic programming approach to create a set of features. These features are used by a linear regression model to estimate the average long-term leakage in DMAs and Shapley values are used to understand the impact and importance of each tree. The methodology is applied to a dataset for a real-world WDN with over 700 DMAs and the results are compared to a previous work which used human-constructed features. The results show comparable performance with significantly fewer, and less complex features. In addition, novel features are found that were not part of the human-constructed features.
- Antonio Candelieri, Dante Conti, and Francesco Archetti. 2014. A Graph based Analysis of Leak Localization in Urban Water Networks. Procedia Engineering 70 (Jan. 2014), 228--237. Google ScholarCross Ref
- Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and T. Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6, 2 (April 2002), 182--197. Google ScholarDigital Library
- Pedro G. Espejo, Sebastián Ventura, and Francisco Herrera. 2010. A Survey on the Application of Genetic Programming to Classification. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 40, 2 (March 2010), 121--144. Google ScholarCross Ref
- Qinglan Fan, Ying Bi, Bing Xue, and Mengjie Zhang. 2022. Genetic programming for feature extraction and construction in image classification. Applied Soft Computing 118 (March 2022), 108509. Google ScholarDigital Library
- Malcolm Farley and Stuart Trow. 2005. Losses in Water Distribution Networks: A Practitioners' Guide to Assessment, Monitoring and Control. Vol. 4. IWA Publishing, London, UK. Google ScholarCross Ref
- Félix-Antoine Fortin, François-Michel De Rainville, Marc-André Gardner Gardner, Marc Parizeau, and Christian Gagné. 2012. DEAP: evolutionary algorithms made easy. The Journal of Machine Learning Research 13, 1 (July 2012), 2171--2175.Google Scholar
- Vicente J. García, Enrique Cabrera, and Enrique Cabrera, Jr. 2006. The Minimum Night Flow Method Revisited. In Water Distribution Systems Analysis Symposium 2006. ASCE, Cincinnati, Ohio, United States, 1--18. Google ScholarCross Ref
- Alireza Gheisi, Mark Forsyth, and Gholamreza Naser. 2016. Water Distribution Systems Reliability: A Review of Research Literature. Journal of Water Resources Planning and Management 142, 11 (Nov. 2016), 04016047. Google ScholarCross Ref
- Orazio Giustolisi and Dragan A. Savic. 2006. A symbolic data-driven technique based on evolutionary polynomial regression. Journal of Hydroinformatics 8, 3 (July 2006), 207--222. Google ScholarCross Ref
- Ling Guo, Daniel Rivero, Julián Dorado, Cristian R. Munteanu, and Alejandro Pazos. 2011. Automatic feature extraction using genetic programming: An application to epileptic EEG classification. Expert Systems with Applications 38, 8 (Aug. 2011), 10425--10436. Google ScholarDigital Library
- William L Hamilton. 2020. Graph Representation Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning 14, 3 (2020), 1--159.Google ScholarCross Ref
- Matthew Hayslep, Edward Keedwell, Farmani Raziyeh, and Joshua Pocock. 2023. Understanding district metered area level leakage using explainable machine learning. In IOP Conference Series: Earth and Environmental Science, Vol. 1136. IOP, Bucharest, Romania, 012040. Google ScholarCross Ref
- Manuel Herrera, Edo Abraham, and Ivan Stoianov. 2016. A Graph-Theoretic Framework for Assessing the Resilience of Sectorised Water Distribution Networks. Water Resources Management 30, 5 (March 2016), 1685--1699. Google ScholarCross Ref
- Raed Jafar, Isam Shahrour, and Ilan Juran. 2010. Application of Artificial Neural Networks (ANN) to model the failure of urban water mains. Mathematical and Computer Modelling 51, 9 (May 2010), 1170--1180. Google ScholarDigital Library
- Dongwoo Jang and Gyewoon Choi. 2017. Estimation of Non-Revenue Water Ratio for Sustainable Management Using Artificial Neural Network and Z-Score in Incheon, Republic of Korea. Sustainability 9, 11 (Nov. 2017), 1933. Google ScholarCross Ref
- Dongwoo Jang and Gyewoon Choi. 2018. Estimation of Non-Revenue Water Ratio Using MRA and ANN in Water Distribution Networks. Water 10, 1 (Jan. 2018), 2. Google ScholarCross Ref
- Dongwoo Jang, Hyoseon Park, and Gyewoon Choi. 2018. Estimation of Leakage Ratio Using Principal Component Analysis and Artificial Neural Network in Water Distribution Systems. Sustainability 10, 3 (March 2018), 750. Google ScholarCross Ref
- Konstantinos Kakoudakis, Kourosh Behzadian, Raziyeh Farmani, and David Butler. 2017. Pipeline failure prediction in water distribution networks using evolutionary polynomial regression combined with K-means clustering. Urban Water Journal 14, 7 (Aug. 2017), 737--742. Google ScholarCross Ref
- Hiremagalur K. Kesavan and Muthu Chandrashekar. 1972. Graph-Theoretic Models for Pipe Network Analysis. Journal of the Hydraulics Division 98, 2 (Feb. 1972), 345--364. Google ScholarCross Ref
- Burak Kizilöz. 2021. Prediction model for the leakage rate in a water distribution system. Water Supply 21, 8 (June 2021), 4481--4492. Google ScholarCross Ref
- Nils M. Kriege, Fredrik D. Johansson, and Christopher Morris. 2020. A survey on graph kernels. Applied Network Science 5, 1 (Dec. 2020), 1--42. Google ScholarCross Ref
- Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc., Long Beach, CA, USA, 1--10. Google ScholarDigital Library
- David J. Montana. 1995. Strongly Typed Genetic Programming. Evolutionary Computation 3, 2 (June 1995), 199--230. Google ScholarDigital Library
- Tianwei Mu, Manhong Huang, Shi Tang, Rui Zhang, Gang Chen, and Baiyi Jiang. 2022. Sensor Partitioning Placements via Random Walk and Water Quality and Leakage Detection Models within Water Distribution Systems. Water Resources Management 36, 13 (Oct. 2022), 5297--5311. Google ScholarCross Ref
- Tianwei Mu, Yan Lu, Haoqiang Tan, Haowen Zhang, and Chengzhi Zheng. 2021. Random Walks Partitioning and Network Reliability Assessing in Water Distribution System. Water Resources Management 35, 8 (June 2021), 2325--2341. Google ScholarCross Ref
- D. Kelly O'Day. 1982. Organizing and analyzing leak and break data for making main replacement decisions. American Water Works Association 74, 11 (1982), 588--594. http://www.jstor.org/stable/41271411Google ScholarCross Ref
- Ofwat. 2021. Service and delivery report 2020-21. Comparative reports and data. Ofwat. 29 pages. https://www.ofwat.gov.uk/publication/service-and-delivery-2020-21/Google Scholar
- Raido Puust, Zoran Kapelan, Dragan Savic, and Tiit Koppel. 2010. A review of methods for leakage management in pipe networks. Urban Water Journal 7, 1 (Feb. 2010), 25--45. Google ScholarCross Ref
- Aravind Rajeswaran, Sridharakumar Narasimhan, and Shankar Narasimhan. 2018. A graph partitioning algorithm for leak detection in water distribution networks. Computers & Chemical Engineering 108 (Jan. 2018), 11--23. Google ScholarCross Ref
- Domonic Searson, David Leahy, and Mark Willis. 2010. GPTIPS: An Open Source Genetic Programming Toolbox For Multigene Symbolic Regression. In International MultiConference of Engineers and Computer Scientists 2010 (Lecture Notes in Engineering and Computer Science, Vol. 1). Newswood Ltd, Hong Kong, 77--80.Google Scholar
- Ling Shao, Li Liu, and Xuelong Li. 2014. Feature Learning for Image Classification Via Multiobjective Genetic Programming. IEEE Transactions on Neural Networks and Learning Systems 25, 7 (July 2014), 1359--1371. Google ScholarCross Ref
- Matthew Smith and Larry Bull. 2007. Improving the human readability of features constructed by genetic programming. In Proceedings of the 9th annual conference on Genetic and evolutionary computation (GECCO '07). Association for Computing Machinery, New York, NY, USA, 1694--1701. Google ScholarDigital Library
- Matthew G. Smith and Larry Bull. 2005. Genetic Programming with a Genetic Algorithm for Feature Construction and Selection. Genetic Programming and Evolvable Machines 6, 3 (Sept. 2005), 265--281. Google ScholarDigital Library
- Peter van Thienen. 2022. Direct assessment of background leakage levels for individual district metered areas (DMAs) using correspondence of demand characteristics between DMAs. Water Supply 22, 7 (July 2022), 6370--6388. Google ScholarCross Ref
- Garðar Örn Garðarsson, Francesca Boem, and Laura Toni. 2022. Graph-Based Learning for Leak Detection and Localisation in Water Distribution Networks*. IFAC-PapersOnLine 55, 6 (Jan. 2022), 661--666. Google ScholarCross Ref
Index Terms
- Multi-Objective Multi-Gene Genetic Programming for the Prediction of Leakage in Water Distribution Networks
Recommendations
Leakage- and variability-conscious circuit designs for the 0.5-v nanoscale CMOS era
ISLPED '09: Proceedings of the 2009 ACM/IEEE international symposium on Low power electronics and designLow-voltage scaling limitations of memory-rich CMOS LSIs are one of the major problems in the nanoscale era because they cause the evermore-serious power crisis with device scaling. The problems stem from two unscalable device parameters: The first is ...
Genetic programming for feature extraction and construction in image classification
AbstractGenetic Programming (GP) has been successfully applied to image classification and achieved promising results. However, most existing methods either address binary image classification tasks only or need a predefined classifier to ...
Highlights- A new GP representation to get an effective combination of features and classifiers.
A hybrid multiple feature construction approach for classification using Genetic Programming
AbstractThe purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based ...
Highlights- A GP-based hybrid feature construction approach is developed.
- A multiple ...
Comments