{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T23:50:48Z","timestamp":1774569048135,"version":"3.50.1"},"reference-count":38,"publisher":"American Geophysical Union (AGU)","issue":"3","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":4,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["agupubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Water Resources Research"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper presents a topology\u2010aware neural network approach for the detection, location, and quantification of abnormal consumptions in water distribution networks. The approach includes two main steps: the optimization of pressure sensor locations to maximize measurement sensitivity and the development of metamodels based on near real\u2010time data. The metamodel is designed and trained to predict the consumptions at all nodes based on pressure measurements and users' consumption collected by smart meters. These nodal consumptions deduced from the actual measured consumption allow the location of potential abnormal uses in the network. The proposed methodology enables the development of two metamodels, each tailored to specific applications based on the training data. The Static Metamodel relies on pressure head measurements under the assumption of constant nodal consumption, whereas the Dynamic Metamodel accounts for daily consumption variations, enabling the detection and location of abnormal consumption in real\u2010world scenarios. Both metamodels can detect the location of abnormal consumptions with reasonable accuracy, although this accuracy strongly depends on the number and spatial distribution of sensors, as well as the magnitude and location of the abnormal consumption. As water utilities implement advanced metering systems, the application of the proposed approach becomes more viable, enabling more effective and faster abnormal consumption detection.<\/jats:p>","DOI":"10.1029\/2025wr041195","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T12:21:42Z","timestamp":1772972502000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Topology\u2010Aware Neural Networks for Abnormal Consumption Detection and Location in Water Distribution Networks"],"prefix":"10.1029","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8537-3169","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Caetano","sequence":"first","affiliation":[{"name":"CERIS Instituto Superior T\u00e9cnico Universidade de Lisboa  Lisboa Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2474-7665","authenticated-orcid":false,"given":"Nelson","family":"Carri\u00e7o","sequence":"additional","affiliation":[{"name":"CERIS Instituto Superior T\u00e9cnico Universidade de Lisboa  Lisboa Portugal"},{"name":"Instituto Superior de Engenharia de Lisboa Instituto Polit\u00e9cnico de Lisboa  Lisboa Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0616-2281","authenticated-orcid":false,"given":"Bruno","family":"Brentan","sequence":"additional","affiliation":[{"name":"Hydraulic Engineering and Water Resources Department School of Engineering Federal University of Minas Gerais  Belo Horizonte Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0778-9721","authenticated-orcid":false,"given":"Andrea","family":"Menapace","sequence":"additional","affiliation":[{"name":"Institute for Renewable Energy Eurac Research  Bozen\u2010Bolzano Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6901-4767","authenticated-orcid":false,"given":"D\u00eddia","family":"Covas","sequence":"additional","affiliation":[{"name":"CERIS Instituto Superior T\u00e9cnico Universidade de Lisboa  Lisboa Portugal"}]}],"member":"13","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.114926"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.122201"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990567"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733\u20109496(2005)131:3(172)"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0000052"},{"key":"e_1_2_10_7_1","unstructured":"Brody S. Alon U. &Yahav E.(2021).How attentive are graph attention networks?Retrieved fromhttp:\/\/arxiv.org\/abs\/2105.14491"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"Caetano J. Ferreira B. Carri\u00e7o N. &Covas D.(2025).Redundancy\u2010driven resilience in optimal design of water distribution networks.https:\/\/doi.org\/10.1061\/JWRMD5.WRENG\u20106613","DOI":"10.1061\/JWRMD5.WRENG-6613"},{"key":"e_1_2_10_9_1","unstructured":"Daniel I. &Cominola A.(2023).Estimating irregular water demands with physics\u2010informed machine learning to inform leakage detection. Retrieved fromhttp:\/\/arxiv.org\/abs\/2309.02935"},{"key":"e_1_2_10_10_1","unstructured":"Defferrard M. Bresson X. &Vandergheynst P.(2016).Convolutional neural networks on graphs with fast localized spectral filtering. Retrieved fromhttp:\/\/arxiv.org\/abs\/1606.09375"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11269\u2010024\u201003983\u2010w"},{"key":"e_1_2_10_12_1","unstructured":"Fey M. &Lenssen J. E.(2019).Fast graph representation learning with PyTorch geometric. Retrieved fromhttp:\/\/arxiv.org\/abs\/1903.02428"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1029\/2021WR031808"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.122396"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.121765"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.121933"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2017.06.022"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2023.121018"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.wri.2024.100255"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11269\u2010017\u20101750\u20102"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10228219"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0000030"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2017.03.236"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.203"},{"key":"e_1_2_10_25_1","unstructured":"Paszke A. Gross S. Massa F. Lerer A. Bradbury J. Chanan G. et\u00a0al. (2019).PyTorch: An imperative style high\u2010performance deep learning library. Retrieved fromhttp:\/\/arxiv.org\/abs\/1912.01703"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1029\/2011WR011527"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0001542"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0001079"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)HY.1943\u20107900.0000703"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1029\/2023WR036741"},{"key":"e_1_2_10_31_1","unstructured":"Veli\u010dkovi\u0107 P. Cucurull G. Casanova A. Romero A. Li\u00f2 P. &Bengio Y.(2017).Graph attention networks. Retrieved fromhttp:\/\/arxiv.org\/abs\/1710.10903"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0001601"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/1573062X.2017.1279191"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.122471"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943\u20105452.0001550"},{"key":"e_1_2_10_36_1","unstructured":"Xu K. Hu W. Leskovec J. &Jegelka S.(2018).How powerful are graph neural networks?Retrieved fromhttp:\/\/arxiv.org\/abs\/1810.00826"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2023.120264"},{"key":"e_1_2_10_38_1","unstructured":"Zhang Z. &Fink O.(2024).Algorithm\u2010informed graph neural networks for leakage detection and localization in water distribution networks. Retrieved fromhttp:\/\/arxiv.org\/abs\/2408.02797"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.115058"}],"container-title":["Water Resources Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2025WR041195","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/full-xml\/10.1029\/2025WR041195","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2025WR041195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T22:57:47Z","timestamp":1774565867000},"score":1,"resource":{"primary":{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/10.1029\/2025WR041195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1029\/2025WR041195"],"URL":"https:\/\/doi.org\/10.1029\/2025wr041195","archive":["Portico"],"relation":{},"ISSN":["0043-1397","1944-7973"],"issn-type":[{"value":"0043-1397","type":"print"},{"value":"1944-7973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"2025-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2025WR041195"}}