{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,8]],"date-time":"2026-11-08T12:38:21Z","timestamp":1794141501134,"version":"4.8.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52400113"],"award-info":[{"award-number":["52400113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52400116"],"award-info":[{"award-number":["52400116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007929","name":"Ningbo Municipal Bureau of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007929","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013263","name":"CityU SKLMP","doi-asserted-by":"publisher","award":["SCRF\/0063"],"award-info":[{"award-number":["SCRF\/0063"]}],"id":[{"id":"10.13039\/100013263","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":[[2026,1]]},"DOI":"10.1016\/j.watres.2025.124901","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:46:58Z","timestamp":1762274818000},"page":"124901","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":9,"special_numbering":"PA","title":["A knowledge-data fusion framework accelerates deep reinforcement learning for real-time control of urban drainage systems"],"prefix":"10.1016","volume":"289","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9418-6306","authenticated-orcid":false,"given":"Wenchong","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6898-2176","authenticated-orcid":false,"given":"Zhiyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hexiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-7460","authenticated-orcid":false,"given":"Zhenliang","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunlun","family":"Xin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.watres.2025.124901_bib0001","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"12","key":"10.1016\/j.watres.2025.124901_bib0002","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1038\/s44221-023-00167-5","article-title":"Association of flooding exposure with cause-specific mortality in North Carolina, United States","volume":"1","author":"Ban","year":"2023","journal-title":"Nat. Water"},{"issue":"3","key":"10.1016\/j.watres.2025.124901_bib0003","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. Hydroinform."},{"issue":"4","key":"10.1016\/j.watres.2025.124901_bib0004","doi-asserted-by":"crossref","first-page":"4018","DOI":"10.1109\/TKDE.2021.3137310","article-title":"Large-scale interactive recommendation with tree-structured reinforcement learning","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"8026","key":"10.1016\/j.watres.2025.124901_bib0005","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1038\/s41586-024-07711-7","article-title":"Loss of plasticity in deep continual learning","volume":"632","author":"Dohare","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.watres.2025.124901_bib0006","article-title":"Making waves: knowledge and data fusion in urban water modelling","volume":"24","author":"Duan","year":"2024","journal-title":"Water Res. X"},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0007","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.1038\/s41467-025-56408-6","article-title":"Deep reinforcement learning for active flow control in a turbulent separation bubble","volume":"16","author":"Font","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.watres.2025.124901_bib0008","series-title":"Proceedings of the 41st International Conference on Machine Learning","article-title":"Stochastic Q-learning for large discrete action spaces","author":"Fourati","year":"2024"},{"issue":"2","key":"10.1016\/j.watres.2025.124901_bib0009","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.envsoft.2007.06.003","article-title":"Multiple objective optimal control of integrated urban wastewater systems","volume":"23","author":"Fu","year":"2008","journal-title":"Environ. Model. Softw."},{"key":"10.1016\/j.watres.2025.124901_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2022.118973","article-title":"The role of deep learning in urban water management: a critical review","volume":"223","author":"Fu","year":"2022","journal-title":"Water Res."},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0011","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.watres.2025.124901_bib0012","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.advwatres.2015.08.007","article-title":"Modeling and real-time control of urban drainage systems: a review","volume":"85","author":"Garc\u00eda","year":"2015","journal-title":"Adv. Water Resour."},{"key":"10.1016\/j.watres.2025.124901_bib0013","series-title":"Proceedings of the 35th International Conference on Machine Learning (Vol. 80, pp. 1861\u20131870). PMLR","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0014","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1038\/s41545-025-00512-z","article-title":"Pollution-based integrated real-time control for urban drainage systems: a multi-agent deep reinforcement learning approach","volume":"8","author":"Huang","year":"2025","journal-title":"NPJ Clean Water"},{"issue":"12","key":"10.1016\/j.watres.2025.124901_bib0015","first-page":"57","article-title":"Optimization of real-time control with green and gray infrastructure design for a cost-effective mitigation of combined sewer overflows","author":"Jean","year":"2021","journal-title":"Water Resour. Res."},{"issue":"2","key":"10.1016\/j.watres.2025.124901_bib0016","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1038\/s44221-023-00032-5","article-title":"Controlling floods in megacities with no regrets","volume":"1","author":"King","year":"2023","journal-title":"Nat. Water"},{"key":"10.1016\/j.watres.2025.124901_bib0017","series-title":"Proceedings of the 5th Conference on Robot Learning (Vol. 164, pp. 1752\u20131757). PMLR","article-title":"Understanding the world through action","author":"Levine","year":"2022"},{"key":"10.1016\/j.watres.2025.124901_bib0018","unstructured":"Levine, S., Kumar, A., Tucker, G., & Fu, J. (2020). Offline Reinforcement Learning: tutorial, review, and perspectives on open problems (No. arXiv:2005.01643). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2005.01643."},{"issue":"12","key":"10.1016\/j.watres.2025.124901_bib0019","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."},{"key":"10.1016\/j.watres.2025.124901_bib0020","unstructured":"Liu, Z., Yang, X., Liu, Z., Xia, Y., Jiang, W., Zhang, Y., Li, L., Fan, G., Song, L., & Jiang, B. (2024). Knowing what not to do: leverage language model insights for action space pruning in multi-agent reinforcement learning (No. arXiv:2405.16854). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2405.16854."},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0021","doi-asserted-by":"crossref","first-page":"3591","DOI":"10.1038\/s41467-025-58439-5","article-title":"Identifying potential risk genes for clear cell renal cell carcinoma with deep reinforcement learning","volume":"16","author":"Lu","year":"2025","journal-title":"Nat. Commun."},{"issue":"3","key":"10.1016\/j.watres.2025.124901_bib0022","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1080\/10643389.2018.1455484","article-title":"Model predictive control of urban drainage systems: a review and perspective towards smart real-time water management","volume":"48","author":"Lund","year":"2018","journal-title":"Crit. Rev. Environ. Sci. Technol."},{"key":"10.1016\/j.watres.2025.124901_bib0023","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Where to add actions in Human-in-the-loop reinforcement learning","volume":"31","author":"Mandel","year":"2017"},{"issue":"7540","key":"10.1016\/j.watres.2025.124901_bib0024","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.2025.124901_bib0025","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.2025.124901_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2024.121145","article-title":"Deep reinforcement learning challenges and opportunities for urban water systems","volume":"253","author":"Negm","year":"2024","journal-title":"Water Res."},{"key":"10.1016\/j.watres.2025.124901_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.jenvman.2021.113810","article-title":"Investigating the impact of sewer overflow on the environment: a comprehensive literature review paper","volume":"301","author":"Owolabi","year":"2022","journal-title":"J. Environ. Manag."},{"key":"10.1016\/j.watres.2025.124901_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.jenvman.2024.121133","article-title":"Real-time control of urban drainage systems using neuro-evolution","volume":"360","author":"Pei","year":"2024","journal-title":"J. Environ. Manag."},{"key":"10.1016\/j.watres.2025.124901_bib0029","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.envsci.2019.05.020","article-title":"Developing knowledge systems for urban resilience to cloudburst rain events","volume":"99","author":"Rosenzweig","year":"2019","journal-title":"Environ. Sci. Policy"},{"issue":"11","key":"10.1016\/j.watres.2025.124901_bib0030","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.2025.124901_bib0031","series-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","first-page":"2067","article-title":"Trial without error: towards safe reinforcement learning via Human intervention","author":"Saunders","year":"2018"},{"key":"10.1016\/j.watres.2025.124901_bib0032","series-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37","first-page":"1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"10.1016\/j.watres.2025.124901_bib0033","series-title":"Proceedings of the 40th International Conference on Machine Learning (Vol. 202, pp. 32145\u201332168). PMLR","article-title":"The dormant neuron phenomenon in deep reinforcement learning","author":"Sokar","year":"2023"},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0034","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.watres.2025.124901_bib0035","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":"29","key":"10.1016\/j.watres.2025.124901_bib0036","doi-asserted-by":"crossref","first-page":"29857","DOI":"10.1007\/s11356-019-06156-0","article-title":"Transfer learning for neural network model in chlorophyll-a dynamics prediction","volume":"26","author":"Tian","year":"2019","journal-title":"Environ. Sci. Pollut. Res."},{"issue":"7","key":"10.1016\/j.watres.2025.124901_bib0037","first-page":"58","article-title":"Flooding and overflow mitigation using deep reinforcement learning based on Koopman operator of Urban drainage systems","author":"Tian","year":"2022","journal-title":"Water Resour. Res."},{"issue":"7","key":"10.1016\/j.watres.2025.124901_bib0038","first-page":"58","article-title":"Combined sewer overflow and flooding mitigation through a reliable real-time control based on multi-reinforcement learning and model predictive control","author":"Tian","year":"2022","journal-title":"Water Resour. Res."},{"issue":"8","key":"10.1016\/j.watres.2025.124901_bib0039","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.2025.124901_bib0040","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."},{"key":"10.1016\/j.watres.2025.124901_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2025.123681","article-title":"Enhancing the resilience of urban drainage system using deep reinforcement learning","volume":"281","author":"Tian","year":"2025","journal-title":"Water Res."},{"issue":"10","key":"10.1016\/j.watres.2025.124901_bib0043","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1080\/1573062X.2021.1943460","article-title":"Quantifying the true potential of real time control in urban drainage systems","volume":"18","author":"Van Der Werf","year":"2021","journal-title":"Urban Water J."},{"issue":"3","key":"10.1016\/j.watres.2025.124901_bib0044","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1007\/s11269-020-02760-9","article-title":"Offline optimization of sluice control rules in the urban water system for flooding mitigation","volume":"35","author":"Wang","year":"2021","journal-title":"Water Resour. Manag."},{"issue":"1","key":"10.1016\/j.watres.2025.124901_bib0045","doi-asserted-by":"crossref","first-page":"2835","DOI":"10.1038\/s41467-025-58192-9","article-title":"Data-driven energy management for electric vehicles using offline reinforcement learning","volume":"16","author":"Wang","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.watres.2025.124901_bib0046","unstructured":"Xie, Z., Lin, Z., Li, J., Li, S., & Ye, D. (2022). Pretraining in deep reinforcement learning: a survey (No. arXiv:2211.03959). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2211.03959."},{"key":"10.1016\/j.watres.2025.124901_bib0047","article-title":"Hospitalization risks associated with floods in a multi-country study","author":"Yang","year":"2025","journal-title":"Nat. Water"},{"key":"10.1016\/j.watres.2025.124901_bib0048","series-title":"2022 IEEE 16th International Conference on Anti-Counterfeiting, Security, and Identification (ASID)","first-page":"161","article-title":"Safe deep reinforcement learning based on sample value evaluation","author":"Ye","year":"2022"},{"issue":"3","key":"10.1016\/j.watres.2025.124901_bib0049","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1038\/s44221-024-00210-z","article-title":"Strategic storm flood evacuation planning for large coastal cities enables more effective transfer of elderly populations","volume":"2","author":"Yin","year":"2024","journal-title":"Nat.Water"},{"key":"10.1016\/j.watres.2025.124901_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.jenvman.2022.116448","article-title":"Evaluation of uncertain signals\u2019 impact on deep reinforcement learning-based real-time control strategy of urban drainage systems","volume":"324","author":"Zhang","year":"2022","journal-title":"J. Environ. Manag."},{"key":"10.1016\/j.watres.2025.124901_bib0051","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.2025.124901_bib0053","series-title":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","first-page":"1","article-title":"An overview of the action space for deep reinforcement learning","author":"Zhu","year":"2021"}],"container-title":["Water Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0043135425018044?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0043135425018044?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T15:38:38Z","timestamp":1766072318000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0043135425018044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":51,"alternative-id":["S0043135425018044"],"URL":"https:\/\/doi.org\/10.1016\/j.watres.2025.124901","relation":{},"ISSN":["0043-1354"],"issn-type":[{"value":"0043-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A knowledge-data fusion framework accelerates deep reinforcement learning for real-time control of urban drainage systems","name":"articletitle","label":"Article Title"},{"value":"Water Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.watres.2025.124901","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"124901"}}