{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:44:44Z","timestamp":1792107884713,"version":"4.4.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005612","name":"The Water Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005612","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Water Research"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.watres.2026.125797","type":"journal-article","created":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T15:45:44Z","timestamp":1774194344000},"page":"125797","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["Real-time control of urban drainage system for flood and combined sewer overflow mitigation with a novel recurrent deep reinforcement learning framework"],"prefix":"10.1016","volume":"299","author":[{"given":"Enpei","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6879-2567","authenticated-orcid":false,"given":"Xiong (Bill)","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.watres.2026.125797_bib0001","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1016\/j.jhydrol.2018.09.044","article-title":"Model predictive control for optimising the operation of urban drainage systems","volume":"566","author":"Abou Rjeily","year":"2018","journal-title":"J. Hydrol."},{"issue":"6","key":"10.1016\/j.watres.2026.125797_bib0002","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: a brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"issue":"5","key":"10.1016\/j.watres.2026.125797_bib0003","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1080\/1573062X.2013.790980","article-title":"Real time control (rtc) of urban drainage systems\u2013a discussion of the additional efforts compared to conventionally operated systems","volume":"10","author":"Beeneken","year":"2013","journal-title":"Urban Water J."},{"issue":"15","key":"10.1016\/j.watres.2026.125797_bib0004","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1080\/10643389.2020.1757957","article-title":"Combined sewer overflows: a critical review on best practice and innovative solutions to mitigate impacts on environment and human health","volume":"51","author":"Botturi","year":"2021","journal-title":"Crit. Rev. Environ. Sci. Technol."},{"issue":"3","key":"10.1016\/j.watres.2026.125797_bib0005","doi-asserted-by":"crossref","first-page":"529","DOI":"10.2166\/hydro.2020.080","article-title":"Flood mitigation in coastal urban catchments using real-time stormwater infrastructure control and reinforcement learning","volume":"23","author":"Bowes","year":"2021","journal-title":"J. Hydroinformatics"},{"issue":"10","key":"10.1016\/j.watres.2026.125797_bib0006","first-page":"2065","article-title":"Reinforcement learning-based real-time control of coastal urban stormwater systems to mitigate flooding and improve water quality","volume":"8","author":"Bowes","year":"2022","journal-title":"Environ. Sci.: Water Res. Technol."},{"issue":"4","key":"10.1016\/j.watres.2026.125797_bib0007","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.envsoft.2004.02.003","article-title":"Integrating simulation models with a view to optimal control of urban wastewater systems","volume":"20","author":"Butler","year":"2005","journal-title":"Environ. Model. Softw."},{"issue":"12","key":"10.1016\/j.watres.2026.125797_bib0008","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.3390\/pr8121595","article-title":"Distributed model predictive control applied to a sewer system","volume":"8","author":"Cembell\u00edn","year":"2020","journal-title":"Processes"},{"key":"10.1016\/j.watres.2026.125797_bib0009","series-title":"A Novel Machine Learning Based Cluster-Then-Forecast Framework For Sensor Placement Optimization and Real-Time Water Level Prediction in Low Impact Development (LID) Stormwater System","author":"Chen","year":"2025"},{"key":"10.1016\/j.watres.2026.125797_bib0010","series-title":"Proceedings of the IJCAI 2019 workshop on explainable artificial intelligence","first-page":"1","article-title":"Distilling deep reinforcement learning policies in soft decision trees","author":"Coppens","year":"2019"},{"issue":"1","key":"10.1016\/j.watres.2026.125797_bib0011","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.watres.2026.125797_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2025.124272","article-title":"Filling data gaps in urban drainage networks: an automated graph theory framework for data collection and reconstruction","author":"Hajibabaei","year":"2025","journal-title":"Water Res."},{"key":"10.1016\/j.watres.2026.125797_bib0013","series-title":"AAAI Fall Symposia","first-page":"141","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2015"},{"key":"10.1016\/j.watres.2026.125797_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.envsoft.2024.106301","article-title":"An explicit robust optimization framework for multipurpose cascade reservoir operation considering inflow uncertainty","volume":"185","author":"He","year":"2025","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.watres.2026.125797_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.jenvman.2021.114009","article-title":"Cost\/benefit assessment of green infrastructure: spatial scale effects on uncertainty and sensitivity","volume":"302","author":"Heidari","year":"2022","journal-title":"J. Environ. Manag."},{"issue":"7","key":"10.1016\/j.watres.2026.125797_bib0016","doi-asserted-by":"crossref","first-page":"139","DOI":"10.3390\/hydrology10070139","article-title":"Predictive MPC-based operation of urban drainage systems using input data-clustered artificial neural networks rainfall forecasting models","volume":"10","author":"Jafari","year":"2023","journal-title":"Hydrology"},{"key":"10.1016\/j.watres.2026.125797_bib0017","series-title":"Geo-Risk 2023","first-page":"156","article-title":"Analyses of frost susceptible flexible pavement adaption for climate change","author":"Jiang","year":"2023"},{"issue":"4","key":"10.1016\/j.watres.2026.125797_bib0018","article-title":"Synthetic storm pattern for drainage design","volume":"83","author":"Keifer","year":"1957","journal-title":"J. Hydraul. Div."},{"issue":"6","key":"10.1016\/j.watres.2026.125797_bib0019","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","article-title":"Optimal and autonomous control using reinforcement learning: a survey","volume":"29","author":"Kiumarsi","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"12","key":"10.1016\/j.watres.2026.125797_bib0020","doi-asserted-by":"crossref","first-page":"4469","DOI":"10.1007\/s11269-022-03221-1","article-title":"Comparison of real-time control methods for CSO reduction with two evaluation indices: computing load rate and double baseline normalized distance","volume":"36","author":"Liao","year":"2022","journal-title":"Water Resour. Manag."},{"issue":"8","key":"10.1016\/j.watres.2026.125797_bib0021","doi-asserted-by":"crossref","DOI":"10.1029\/2019WR026272","article-title":"CSO reduction by integrated model predictive control of stormwater inflows: a simulated proof of concept using linear surrogate models","volume":"56","author":"Lund","year":"2020","journal-title":"Water Resour. Res."},{"key":"10.1016\/j.watres.2026.125797_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2022.119350","article-title":"Optimization of in-pipe storage capacity use in urban drainage systems with improved DP considering the time lag of flow routing","volume":"227","author":"Luo","year":"2022","journal-title":"Water Res."},{"issue":"15","key":"10.1016\/j.watres.2026.125797_bib0023","doi-asserted-by":"crossref","first-page":"5241","DOI":"10.1007\/s11269-018-2157-4","article-title":"A hybrid surrogate modelling strategy for simplification of detailed urban drainage simulators","volume":"32","author":"Mahmoodian","year":"2018","journal-title":"Water Resour. Manag."},{"key":"10.1016\/j.watres.2026.125797_bib0024","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.jhydrol.2015.01.063","article-title":"Relationships between rainfall and Combined Sewer Overflow (CSO) occurrences","volume":"523","author":"Mailhot","year":"2015","journal-title":"J. Hydrol."},{"issue":"52","key":"10.1016\/j.watres.2026.125797_bib0025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.21105\/joss.02292","article-title":"PySWMM: the python interface to stormwater management model (SWMM)","volume":"5","author":"McDonnell","year":"2020","journal-title":"J. open source softw."},{"key":"10.1016\/j.watres.2026.125797_bib0026","first-page":"345","article-title":"The impacts of urbanisation and climate change on urban flooding and urban water quality: a review of the evidence concerning the United Kingdom","volume":"12","author":"Miller","year":"2017","journal-title":"J. Hydrol.: Reg. Stud."},{"issue":"7540","key":"10.1016\/j.watres.2026.125797_bib0027","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.watres.2026.125797_bib0028","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1016\/j.scitotenv.2014.10.087","article-title":"Using data from monitoring combined sewer overflows to assess, improve, and maintain combined sewer systems","volume":"505","author":"Montserrat","year":"2015","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.watres.2026.125797_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.advwatres.2020.103600","article-title":"Deep reinforcement learning for the real time control of stormwater systems","volume":"140","author":"Mullapudi","year":"2020","journal-title":"Adv. Water Resour."},{"key":"10.1016\/j.watres.2026.125797_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2022.118972","article-title":"Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning","volume":"223","author":"Palmitessa","year":"2022","journal-title":"Water Res."},{"key":"10.1016\/j.watres.2026.125797_bib0032","first-page":"331","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handb. Oper. Res. Manag. Sci."},{"key":"10.1016\/j.watres.2026.125797_bib0033","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10584-011-0149-y","article-title":"RCP 8.5\u2014A scenario of comparatively high greenhouse gas emissions","volume":"109","author":"Riahi","year":"2011","journal-title":"Clim. change"},{"key":"10.1016\/j.watres.2026.125797_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.envsoft.2019.07.009","article-title":"Leveraging open source software and parallel computing for model predictive control of urban drainage systems using EPA-SWMM5","volume":"120","author":"Sadler","year":"2019","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.watres.2026.125797_bib0035","series-title":"Internet of Things for Sustainable Community Development: Wireless Communications, Sensing, and Systems","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/978-3-031-62162-8_9","article-title":"Internet of things in water management and treatment","author":"Salam","year":"2024"},{"issue":"11","key":"10.1016\/j.watres.2026.125797_bib0036","doi-asserted-by":"crossref","first-page":"3222","DOI":"10.3390\/w12113222","article-title":"Deep reinforcement learning with uncertain data for real-time stormwater system control and flood mitigation","volume":"12","author":"Saliba","year":"2020","journal-title":"Water"},{"key":"10.1016\/j.watres.2026.125797_bib0037","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/A:1005621523177","article-title":"Climate change impacts on urban flooding","volume":"47","author":"Schreider","year":"2000","journal-title":"Clim. Change"},{"key":"10.1016\/j.watres.2026.125797_bib0038","series-title":"Reinforcement Learning: State-of-the-Art","first-page":"387","article-title":"Partially observable Markov decision processes","author":"Spaan","year":"2012"},{"issue":"6","key":"10.1016\/j.watres.2026.125797_bib0040","doi-asserted-by":"crossref","first-page":"2968","DOI":"10.1109\/TCST.2023.3286648","article-title":"Model predictive control of urban drainage systems considering uncertainty","volume":"31","author":"Svensen","year":"2023","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"10.1016\/j.watres.2026.125797_bib0041","unstructured":"Szepesv\u00e1ri, C. (2009). Reinforcement learning algorithms for MDPs."},{"issue":"1","key":"10.1016\/j.watres.2026.125797_bib0042","article-title":"Climate change impact on flood and extreme precipitation increases with water availability","volume":"10","author":"Tabari","year":"2020","journal-title":"Sci. Rep."},{"key":"10.1016\/j.watres.2026.125797_bib0043","unstructured":"Tessler, C., Mankowitz, D.J., & Mannor, S. (2018). Reward constrained policy optimization. arXiv preprint arXiv:1805.11074."},{"key":"10.1016\/j.watres.2026.125797_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2023.120912","article-title":"Improving the interpretability of deep reinforcement learning in urban drainage system operation","volume":"249","author":"Tian","year":"2024","journal-title":"Water Res."},{"issue":"7","key":"10.1016\/j.watres.2026.125797_bib0045","doi-asserted-by":"crossref","DOI":"10.1029\/2021WR030939","article-title":"Flooding and overflow mitigation using deep reinforcement learning based on Koopman operator of urban drainage systems","volume":"58","author":"Tian","year":"2022","journal-title":"Water Resour. Res."},{"issue":"7","key":"10.1016\/j.watres.2026.125797_bib0046","doi-asserted-by":"crossref","DOI":"10.1029\/2021WR030703","article-title":"Combined sewer overflow and flooding mitigation through a reliable real-time control based on multi-reinforcement learning and model predictive control","volume":"58","author":"Tian","year":"2022","journal-title":"Water Resour. Res."},{"issue":"8","key":"10.1016\/j.watres.2026.125797_bib0047","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.3390\/w15081528","article-title":"State selection and cost estimation for deep reinforcement learning-based real-time control of urban drainage system","volume":"15","author":"Tian","year":"2023","journal-title":"Water"},{"key":"10.1016\/j.watres.2026.125797_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhydrol.2023.129435","article-title":"Flooding mitigation through safe & trustworthy reinforcement learning","volume":"620","author":"Tian","year":"2023","journal-title":"J. Hydrol."},{"issue":"1","key":"10.1016\/j.watres.2026.125797_bib0049","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1007\/s10661-025-14814-9","article-title":"Cost-effective drone monitoring and evaluating toolkits for stream habitat health: development and application","volume":"198","author":"Wang","year":"2026","journal-title":"Environ. Monit. Assess."},{"key":"10.1016\/j.watres.2026.125797_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhydrol.2025.132998","article-title":"Improved non-dominated sorting genetic algorithm III for efficient of multi-objective cascade reservoirs scheduling under different hydrological conditions","volume":"656","author":"Wang","year":"2025","journal-title":"J. Hydrol."},{"issue":"3","key":"10.1016\/j.watres.2026.125797_bib0051","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1002\/2014RG000464","article-title":"Future changes to the intensity and frequency of short-duration extreme rainfall","volume":"52","author":"Westra","year":"2014","journal-title":"Rev. Geophys."},{"issue":"3","key":"10.1016\/j.watres.2026.125797_bib0052","first-page":"729","article-title":"Reinforcement learning","volume":"12","author":"Wiering","year":"2012","journal-title":"Adapt. Learn. Optim."},{"key":"10.1016\/j.watres.2026.125797_bib0053","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.jhydrol.2013.05.037","article-title":"Revision of urban drainage design rules after assessment of climate change impacts on precipitation extremes at Uccle, Belgium","volume":"496","author":"Willems","year":"2013","journal-title":"J. Hydrol."},{"issue":"3","key":"10.1016\/j.watres.2026.125797_bib0054","doi-asserted-by":"crossref","DOI":"10.1061\/JSENDH.STENG-12718","article-title":"Machine learning\u2013aided rapid estimation of multilevel capacity of flexure-identified circular concrete bridge columns with corroded reinforcement","volume":"150","author":"Xu","year":"2024","journal-title":"J. Struct. Eng."},{"key":"10.1016\/j.watres.2026.125797_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.scs.2025.106976","article-title":"Urban residential energy consumption under extreme temperatures in China: asymmetric patterns, heterogeneous drivers, and adaptive zoning strategies","author":"Yu","year":"2025","journal-title":"Sustain. Cities Soc."},{"key":"10.1016\/j.watres.2026.125797_bib0056","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2022.119498","article-title":"Towards coordinated and robust real-time control: a decentralized approach for combined sewer overflow and urban flooding reduction based on multi-agent reinforcement learning","volume":"229","author":"Zhang","year":"2023","journal-title":"Water Res."},{"key":"10.1016\/j.watres.2026.125797_bib0057","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2024.122142","article-title":"Graph neural network-based surrogate modelling for real-time hydraulic prediction of urban drainage networks","volume":"263","author":"Zhang","year":"2024","journal-title":"Water Res."},{"key":"10.1016\/j.watres.2026.125797_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.marpolbul.2025.117710","article-title":"Seafloor debris detection using underwater images and deep learning-driven image restoration: a case study from Koh Tao, Thailand","volume":"214","author":"Zhao","year":"2025","journal-title":"Mar. Pollut. Bull."},{"key":"10.1016\/j.watres.2026.125797_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2025.103324","article-title":"Mamba-based super-resolution and semi-supervised YOLOv10 for freshwater mussel detection using acoustic video camera: a case study at Lake Izunuma, Japan","author":"Zhao","year":"2025","journal-title":"Ecol. Inform."},{"issue":"11","key":"10.1016\/j.watres.2026.125797_bib0060","doi-asserted-by":"crossref","first-page":"6721","DOI":"10.1021\/acsestwater.5c00714","article-title":"Observed differences in wastewater measurements of Treponema pallidum, Norovirus, and SARS-CoV-2 in Detroit metropolitan areas with different socioeconomic vulnerabilities","volume":"5","author":"Zhao","year":"2025","journal-title":"ACS ES&T Water"},{"key":"10.1016\/j.watres.2026.125797_bib0061","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/1523908X.2026.2624491","article-title":"Climate promotion tournaments and collaborative governance: central-local dynamics in China\u2019s carbon neutrality policy implementation","author":"Zhou","year":"2026","journal-title":"J. Environ. Policy Plan."}],"container-title":["Water Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0043135426004793?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0043135426004793?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T06:49:57Z","timestamp":1778914197000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0043135426004793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":59,"alternative-id":["S0043135426004793"],"URL":"https:\/\/doi.org\/10.1016\/j.watres.2026.125797","relation":{},"ISSN":["0043-1354"],"issn-type":[{"value":"0043-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Real-time control of urban drainage system for flood and combined sewer overflow mitigation with a novel recurrent deep reinforcement learning framework","name":"articletitle","label":"Article Title"},{"value":"Water Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.watres.2026.125797","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"125797"}}