{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:37:47Z","timestamp":1776886667211,"version":"3.51.2"},"reference-count":43,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T00:00:00Z","timestamp":1727481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61971186"],"award-info":[{"award-number":["61971186"]}]},{"name":"National Natural Science Foundation of China","award":["7"],"award-info":[{"award-number":["7"]}]},{"name":"2019 Hunan High-level Talent Aggregation Project\u2014Innovative Talents","award":["61971186"],"award-info":[{"award-number":["61971186"]}]},{"name":"2019 Hunan High-level Talent Aggregation Project\u2014Innovative Talents","award":["7"],"award-info":[{"award-number":["7"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The efficient detection of leakages in water distribution networks (WDNs) is crucial to ensuring municipal water supply safety and improving urban operations. Traditionally, machine learning methods such as Convolutional Neural Networks (CNNs) and Autoencoders (AEs) have been used for leakage detection. However, these methods heavily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer-based model for detecting leakages in WDNs. The transformer incorporates an attention mechanism to learn data distributions and account for correlations between historical pressure data and data from the same time on different days, thereby emphasizing long-term dependencies in pressure series. Additionally, we apply pressure data normalization across each leakage scenario and concatenate position embeddings with pressure data in the transformer model to avoid feature misleading. The performance of the proposed method is evaluated by using detection accuracy and F1-score. The experimental studies conducted on simulated pressure datasets from three different WDNs demonstrate that the transformer-based model significantly outperforms traditional CNN methods.<\/jats:p>","DOI":"10.3390\/s24196294","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T07:19:37Z","timestamp":1727680777000},"page":"6294","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Transformer-Based Approach to Leakage Detection in Water Distribution Networks"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6097-1559","authenticated-orcid":false,"given":"Juan","family":"Luo","sequence":"first","affiliation":[{"name":"Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China"}]},{"given":"Chongxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore 138632, Singapore"}]},{"given":"Jielong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Internet of Things Engineering, Jiangnan University, Wuxi 214000, China"}]},{"given":"Xionghu","family":"Zhong","sequence":"additional","affiliation":[{"name":"Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2537","DOI":"10.1007\/s11269-021-02847-x","article-title":"Calibration of design models for leakage management of water distribution networks","volume":"35","author":"Berardi","year":"2021","journal-title":"Water Resour. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"387","DOI":"10.2166\/aqua.2012.044","article-title":"Intrusion and leakage in drinking systems induced by pressure variation","volume":"61","author":"Ramos","year":"2012","journal-title":"J. Water Suppl. Res. Technol.\u2014AQUA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106062","DOI":"10.1016\/j.engappai.2023.106062","article-title":"Leakage detection in water distribution networks via 1D CNN deep autoencoder for multivariate SCADA data","volume":"122","author":"Tornyeviadzi","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4759","DOI":"10.1007\/s00521-021-06666-4","article-title":"Leak detection and localization in water distribution networks by combining expert knowledge and data-driven models","volume":"34","author":"Soldevila","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"116098","DOI":"10.1016\/j.enconman.2022.116098","article-title":"Self-powered smart agriculture real-time sensing device based on hybrid wind energy harvesting triboelectric-electromagnetic nanogenerator","volume":"269","author":"Gui","year":"2022","journal-title":"Energy Conv. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"012036","DOI":"10.1088\/1757-899X\/190\/1\/012036","article-title":"Water pipeline monitoring and leak detection using flow liquid meter sensor","volume":"190","author":"Rahmat","year":"2017","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.ifacol.2022.07.646","article-title":"Data-driven leak localization in WDN using pressure sensor and hydraulic information","volume":"55","author":"Alves","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"ref_8","unstructured":"Charalambous, B. (2005, January 12\u201314). Experiences in DMA redesign at the Water Board of Lemesos, Cyprus. Proceedings of the IWA Specialized Conference Leakage, Halifax, NS, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1016\/j.proeng.2014.02.118","article-title":"Spatial and temporal forecasting of water consumption at the DMA level using extensive measurements","volume":"70","author":"Mamade","year":"2014","journal-title":"Procedia Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Adu-Manu, K.S., Adjetey, C., and Apea, N.Y.O. (2022). Leakage Detection and Automatic Billing in Water Distribution Systems Using Smart Sensors. Digital Transformation for Sustainability: ICT-Supported Environmental Socio-Economic Development, Springer.","DOI":"10.1007\/978-3-031-15420-1_12"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"04021071","DOI":"10.1061\/(ASCE)WR.1943-5452.0001465","article-title":"Optimized DMA partition to reduce background leakage rate in water distribution networks","volume":"147","author":"Zhang","year":"2021","journal-title":"J. Water Resour. Plan. Manag."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"782","DOI":"10.2166\/hydro.2021.164","article-title":"Water leakage detection and localization using hydraulic modeling and classification","volume":"23","author":"Mohammed","year":"2021","journal-title":"J. Hydroinform."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"78846","DOI":"10.1109\/ACCESS.2018.2885444","article-title":"Review of current technologies and proposed intelligent methodologies for water distributed network leakage detection","volume":"6","author":"Chan","year":"2018","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"04014070","DOI":"10.1061\/(ASCE)WR.1943-5452.0000464","article-title":"Water distribution system burst detection using a nonlinear Kalman filter","volume":"141","author":"Jung","year":"2015","journal-title":"J. Water Resour. Plan. Manag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.procs.2016.08.141","article-title":"Earnpipe: A testbed for smart water pipeline monitoring using wireless sensor network","volume":"96","author":"Karray","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1061\/(ASCE)WR.1943-5452.0000344","article-title":"Weighted least squares with expectation-maximization algorithm for burst detection in UK water distribution systems","volume":"140","author":"Ye","year":"2014","journal-title":"J. Water Resour. Plan. Manag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4279","DOI":"10.1109\/TIE.2017.2764861","article-title":"Novel leakage detection by ensemble CNN-SVM and graph-based localization in water distribution systems","volume":"65","author":"Kang","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11265-012-0690-6","article-title":"Wavelet-based burst event detection and localization in water distribution systems","volume":"72","author":"Srirangarajan","year":"2013","journal-title":"J. Signal Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"617","DOI":"10.2166\/hydro.2013.057","article-title":"Pattern matching and associative artificial neural networks for water distribution system time series data analysis","volume":"16","author":"Mounce","year":"2016","journal-title":"J. Hydroinform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1061\/(ASCE)WR.1943-5452.0000339","article-title":"Automated detection of pipe bursts and other events in water distribution systems","volume":"140","author":"Romano","year":"2014","journal-title":"J. Water Resour. Plan. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"54","DOI":"10.3390\/ai4010004","article-title":"End-to-End Transformer-Based Models in Textual-Based NLP","volume":"4","author":"Rahali","year":"2023","journal-title":"AI"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"You, J., and Korhonen, J. (2021, January 19\u201322). Transformer for image quality assessment. Proceedings of the 2021 IEEE International Conference on Image Processing, Anchorage, AK, USA.","DOI":"10.1109\/ICIP42928.2021.9506075"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Mohamed, A., Le, D., Liu, C., Xiao, A., Mahadeokar, J., and Seltzer, M.L. (2020, January 4\u20139). Transformer-based acoustic modeling for hybrid speech recognition. Proceedings of the ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing, Virtual.","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1119\/1.2180283","article-title":"Teaching Faraday\u2019s law of electromagnetic induction in an introductory physics course","volume":"74","author":"Galili","year":"2006","journal-title":"Am. J. Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4210","DOI":"10.1109\/JSTARS.2017.2708817","article-title":"Reliability of infrared thermography in detecting leaks in buried water reticulation pipes","volume":"10","author":"Bach","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"10669","DOI":"10.1029\/2019GL084771","article-title":"Rainfall estimation from ground radar and TRMM Precipitation Radar using hybrid deep neural networks","volume":"46","author":"Chandrasekar","year":"2019","journal-title":"Geophys. Res. Lett."},{"key":"ref_27","first-page":"135","article-title":"Leakage detection and localisation in drinking water distribution networks by multiregional PCA","volume":"17","author":"Duzinkiewicz","year":"2008","journal-title":"Stud. Inform. Control"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"307","DOI":"10.2166\/hydro.2021.093","article-title":"Ensemble-based machine learning approach for improved leak detection in water mains","volume":"23","author":"Ravichandran","year":"2021","journal-title":"J. Hydroinform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"109810","DOI":"10.1016\/j.ymssp.2022.109810","article-title":"Leak detection in water distribution systems by classifying vibration signals","volume":"185","author":"Yu","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"127934","DOI":"10.1016\/j.jhydrol.2022.127934","article-title":"Prediction model of drinking water source quality with potential industrial-agricultural pollution based on CNN-GRU-Attention","volume":"610","author":"Mei","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"30457","DOI":"10.1109\/ACCESS.2019.2902711","article-title":"Leak detection and location based on ISLMD and CNN in a pipeline","volume":"7","author":"Zhou","year":"2019","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Javadiha, M., Blesa, J., Soldevila, A., and Puig, V. (2019, January 23\u201326). Leak localization in water distribution networks using deep learning. Proceedings of the 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), Paris, France.","DOI":"10.1109\/CoDIT.2019.8820627"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Leonzio, D.U., Bestagini, P., Marcon, M., Quarta, G.P., and Tubaro, S. (2023, January 4\u201310). Water Leak Detection and Localization using Convolutional Autoencoders. Proceedings of the ICASSP 2023\u20142023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10095760"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1016\/j.compchemeng.2019.03.012","article-title":"Source localization for hazardous material release in an outdoor chemical plant via a combination of LSTM-RNN and CFD simulation","volume":"125","author":"Kim","year":"2019","journal-title":"Comput. Chem. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.watres.2016.05.016","article-title":"Burst detection in district metering areas using a data driven clustering algorithm","volume":"100","author":"Wu","year":"2016","journal-title":"Water Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1080\/09715010.2022.2134742","article-title":"Leak detection in water distribution networks using deep learning","volume":"29","author":"Punukollu","year":"2023","journal-title":"ISH J. Hydraul. Eng."},{"key":"ref_37","unstructured":"Dundar, M., Krishnapuram, B., Bi, J., and Rao, R.B. (2007, January 6\u201312). Learning classifiers when the training data is not IID. Proceedings of the IJCAI, Hyderabad, India."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1111\/j.2044-8317.1997.tb01098.x","article-title":"Some practical reasons for reconsidering the Kolmogorov-Smirnov test","volume":"50","author":"Wilcox","year":"1997","journal-title":"Br. J. Math. Stat. Psychol."},{"key":"ref_39","unstructured":"Huang, X., Shang, H.L., and Siu, T.K. (2023). A nonlinearity and model specification test for functional time series. arXiv."},{"key":"ref_40","unstructured":"Waswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the NIPS, Long Beach, CA, USA."},{"key":"ref_41","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","unstructured":"Vrachimis, S.G., and Kyriakou, M.S. (2018, January 23\u201325). LeakDB: A benchmark dataset for leakage diagnosis in water distribution networks. Proceedings of the WDSA\/CCWI Joint Conference Proceedings, Kingston, ON, Canada."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Klise, K.A., Murray, R., and Haxton, T. (2018, January 23\u201325). An Overview of the Water Network Tool for Resilience (WNTR). Proceedings of the WDSA\/CCWI Joint Conference Proceedings, Kingston, ON, Canada.","DOI":"10.2172\/1376816"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6294\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:06:17Z","timestamp":1760112377000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,28]]},"references-count":43,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["s24196294"],"URL":"https:\/\/doi.org\/10.3390\/s24196294","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,28]]}}}