{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:49:28Z","timestamp":1792054168011,"version":"4.4.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Environmental Research"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.envres.2026.125714","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T15:18:12Z","timestamp":1790003892000},"page":"125714","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["A physically constrained deep learning framework for total nitrogen prediction: A case study of a reservoir in North China"],"prefix":"10.1016","volume":"309","author":[{"given":"Hao","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.envres.2026.125714_bib1","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling (arXiv:1803.01271)","author":"Bai","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.envres.2026.125714_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhydrol.2023.130281","article-title":"Effects of extreme precipitation intensity and duration on the runoff and nutrient yields","volume":"626","author":"Chang","year":"2023","journal-title":"J. Hydrol."},{"issue":"5917","key":"10.1016\/j.envres.2026.125714_bib3","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1126\/science.1167755","article-title":"Controlling eutrophication: Nitrogen and phosphorus","volume":"323","author":"Conley","year":"2009","journal-title":"Science"},{"issue":"4","key":"10.1016\/j.envres.2026.125714_bib4","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/MCI.2015.2471196","article-title":"Learning in nonstationary environments: a survey","volume":"10","author":"Ditzler","year":"2015","journal-title":"IEEE Comput. Intell. Mag."},{"key":"10.1016\/j.envres.2026.125714_bib5","series-title":"2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS)","first-page":"900","article-title":"Combating distribution shift for accurate time series forecasting via hypernetworks","author":"Duan","year":"2023"},{"issue":"2","key":"10.1016\/j.envres.2026.125714_bib6","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"issue":"5878","key":"10.1016\/j.envres.2026.125714_bib7","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1126\/science.1136674","article-title":"Transformation of the nitrogen cycle: recent trends, questions, and potential solutions","volume":"320","author":"Galloway","year":"2008","journal-title":"Science"},{"key":"10.1016\/j.envres.2026.125714_bib8","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2025.103337","article-title":"Kalman filtering assimilated machine learning methods significantly improve the prediction performance of water quality parameters","volume":"90","author":"Gao","year":"2025","journal-title":"Ecol. Inform."},{"issue":"12","key":"10.1016\/j.envres.2026.125714_bib9","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1038\/ngeo2567","article-title":"Denitrification in the Mississippi River network controlled by flow through river bedforms","volume":"8","author":"Gomez-Velez","year":"2015","journal-title":"Nat. Geosci."},{"key":"10.1016\/j.envres.2026.125714_bib10","doi-asserted-by":"crossref","DOI":"10.1016\/j.envsoft.2022.105458","article-title":"Coastal water quality prediction based on machine learning with feature interpretation and spatio-temporal analysis","volume":"155","author":"Grb\u010di\u0107","year":"2022","journal-title":"Environ. Model. Software"},{"key":"10.1016\/j.envres.2026.125714_bib11","article-title":"Deep time series forecasting with shape and temporal criteria (arXiv:2104.04610)","author":"Guen","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.envres.2026.125714_bib12","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2023.166036","article-title":"The influence of wet-to-dry season shifts on the microbial community stability and nitrogen cycle in the Poyang Lake sediment","volume":"903","author":"Guo","year":"2023","journal-title":"Sci. Total Environ."},{"issue":"10","key":"10.1016\/j.envres.2026.125714_bib13","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.3390\/w14101643","article-title":"Prediction of total nitrogen and phosphorus in surface water by deep learning methods based on multi-scale feature extraction","volume":"14","author":"He","year":"2022","journal-title":"Water"},{"issue":"8","key":"10.1016\/j.envres.2026.125714_bib14","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"issue":"1","key":"10.1016\/j.envres.2026.125714_bib15","article-title":"Application of hybrid improved temporal convolution network model in time series prediction of river water quality","volume":"13","author":"Hu","year":"2023","journal-title":"Sci. Rep."},{"issue":"6","key":"10.1016\/j.envres.2026.125714_bib16","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1038\/s41558-024-02007-0","article-title":"Current and future global water scarcity intensifies when accounting for surface water quality","volume":"14","author":"Jones","year":"2024","journal-title":"Nat. Clim. Change"},{"issue":"3","key":"10.1016\/j.envres.2026.125714_bib17","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1007\/s40808-019-00581-3","article-title":"Prediction of water quality index using artificial neural network and multiple linear regression modelling approach in Shivganga River basin, India","volume":"5","author":"Kadam","year":"2019","journal-title":"Model. Earth Syst. Environ."},{"issue":"9","key":"10.1016\/j.envres.2026.125714_bib18","doi-asserted-by":"crossref","first-page":"12875","DOI":"10.1007\/s11356-021-13875-w","article-title":"Water quality assessment of a river using deep learning bi-LSTM methodology: forecasting and validation","volume":"29","author":"Khullar","year":"2022","journal-title":"Environ. Sci. Pollut. Control Ser."},{"key":"10.1016\/j.envres.2026.125714_bib19","series-title":"International Conference on Learning Representations","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","author":"Kim","year":"2021"},{"issue":"5","key":"10.1016\/j.envres.2026.125714_bib20","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1038\/nrmicro.2018.9","article-title":"The microbial nitrogen-cycling network","volume":"16","author":"Kuypers","year":"2018","journal-title":"Nat. Rev. Microbiol."},{"key":"10.1016\/j.envres.2026.125714_bib21","article-title":"TILDE-Q: a transformation invariant loss function for time-series forecasting","author":"Lee","year":"2024","journal-title":"arXiv:2210.15050). arXiv"},{"key":"10.1016\/j.envres.2026.125714_bib22","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecolind.2023.110782","article-title":"A long-term water quality prediction model for marine ranch based on time-graph convolutional neural network","volume":"154","author":"Li","year":"2023","journal-title":"Ecol. Indic."},{"key":"10.1016\/j.envres.2026.125714_bib23","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhydrol.2025.133661","article-title":"Impact of large-scale climate indices on total nitrogen concentrations in drinking water sources cannot be overlooked","volume":"661","author":"Li","year":"2025","journal-title":"J. Hydrol."},{"issue":"18","key":"10.1016\/j.envres.2026.125714_bib24","doi-asserted-by":"crossref","first-page":"26415","DOI":"10.1007\/s11356-024-33058-7","article-title":"Research progress in water quality prediction based on deep learning technology: a review","volume":"31","author":"Li","year":"2024","journal-title":"Environ. Sci. Pollut. Control Ser."},{"key":"10.1016\/j.envres.2026.125714_bib25","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2022.156375","article-title":"How climate change and land-use evolution relates to the non-point source pollution in a typical watershed of China","volume":"839","author":"Li","year":"2022","journal-title":"Sci. Total Environ."},{"issue":"8","key":"10.1016\/j.envres.2026.125714_bib26","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1038\/s41561-024-01484-4","article-title":"Decline in atmospheric nitrogen deposition in China between 2010 and 2020","volume":"17","author":"Liu","year":"2024","journal-title":"Nat. Geosci."},{"key":"10.1016\/j.envres.2026.125714_bib27","doi-asserted-by":"crossref","DOI":"10.1016\/j.envres.2023.115560","article-title":"A novel deep learning ensemble model based on two-stage feature selection and intelligent optimization for water quality prediction","volume":"224","author":"Liu","year":"2023","journal-title":"Environ. Res."},{"key":"10.1016\/j.envres.2026.125714_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jconhyd.2025.104725","article-title":"Water quality prediction method based on a combined machine learning model: a case study of the Daling River Basin","volume":"276","author":"Liu","year":"2026","journal-title":"J. Contam. Hydrol."},{"key":"10.1016\/j.envres.2026.125714_bib29","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2022.160335","article-title":"Spatiotemporal heterogeneity of nitrogen transformation potentials in a freshwater estuarine system","volume":"859","author":"L\u00fc","year":"2023","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envres.2026.125714_bib30","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2022.157013","article-title":"Slight flow volume rises increase nitrogen loading to nitrogen-rich river, while dramatic flow volume rises promote nitrogen consumption","volume":"844","author":"L\u00fc","year":"2022","journal-title":"Sci. Total Environ."},{"issue":"3","key":"10.1016\/j.envres.2026.125714_bib31","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.jhydrol.2010.06.010","article-title":"Impact of climate variability and human activity on streamflow decrease in the Miyun Reservoir catchment","volume":"389","author":"Ma","year":"2010","journal-title":"J. Hydrol."},{"key":"10.1016\/j.envres.2026.125714_bib32","doi-asserted-by":"crossref","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":"10.1016\/j.envres.2026.125714_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2024.170625","article-title":"Multiple isotopes decipher the nitrogen cycle in the cascade reservoirs and downstream in the middle and lower Yellow River: insight for reservoir drainage period","volume":"918","author":"Mu","year":"2024","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envres.2026.125714_bib34","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2024.170765","article-title":"Development of a basin-scale total nitrogen prediction model by integrating clustering and regression methods","volume":"920","author":"Nam","year":"2024","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envres.2026.125714_bib35","article-title":"A time series is worth 64 words: Long-term forecasting with transformers (arXiv:2211.14730v2)","author":"Nie","year":"2022","journal-title":"arXiv"},{"issue":"10","key":"10.1016\/j.envres.2026.125714_bib36","doi-asserted-by":"crossref","first-page":"5519","DOI":"10.1021\/acs.est.7b05950","article-title":"Mitigating the expansion of harmful algal blooms across the freshwater-to-marine continuum","volume":"52","author":"Paerl","year":"2018","journal-title":"Environmental Science & Technology"},{"key":"10.1016\/j.envres.2026.125714_bib37","doi-asserted-by":"crossref","DOI":"10.1016\/j.watres.2024.122777","article-title":"Time series-based machine learning for forecasting multivariate water quality in full-scale drinking water treatment with various reagent dosages","volume":"268","author":"Pang","year":"2025","journal-title":"Water Res."},{"key":"10.1016\/j.envres.2026.125714_bib38","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2024.102514","article-title":"Assessing water quality of an ecologically critical urban canal incorporating machine learning approaches","volume":"80","author":"Sajib","year":"2024","journal-title":"Ecol. Inform."},{"issue":"6349","key":"10.1016\/j.envres.2026.125714_bib39","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1126\/science.aan2409","article-title":"Eutrophication will increase during the 21st century as a result of precipitation changes","volume":"357","author":"Sinha","year":"2017","journal-title":"Science"},{"issue":"7315","key":"10.1016\/j.envres.2026.125714_bib40","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/nature09440","article-title":"Global threats to human water security and river biodiversity","volume":"467","author":"V\u00f6r\u00f6smarty","year":"2010","journal-title":"Nature"},{"key":"10.1016\/j.envres.2026.125714_bib41","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.scitotenv.2019.02.010","article-title":"Meteorological factors and water quality changes of Plateau Lake Dianchi in China (1990\u20132015) and their joint influences on cyanobacterial blooms","volume":"665","author":"Wang","year":"2019","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envres.2026.125714_bib42","doi-asserted-by":"crossref","DOI":"10.1016\/j.envres.2024.119911","article-title":"Hybrid deep learning based prediction for water quality of plain watershed","volume":"262","author":"Wang","year":"2024","journal-title":"Environ. Res."},{"key":"10.1016\/j.envres.2026.125714_bib43","doi-asserted-by":"crossref","DOI":"10.1016\/j.scitotenv.2024.175144","article-title":"Multi-machine learning methods to predict spatial variation characteristics of total nitrogen at watershed scale: evidences from the largest watershed (Yangtze River Watershed), Asian","volume":"949","author":"Wang","year":"2024","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.envres.2026.125714_bib44","article-title":"TimesNet: temporal 2D-variation modeling for general time series analysis (arXiv:2210.02186)","author":"Wu","year":"2023","journal-title":"arXiv"},{"issue":"6","key":"10.1016\/j.envres.2026.125714_bib45","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1039\/C8EM00042E","article-title":"The cycle of nitrogen in river systems: sources, transformation, and flux","volume":"20","author":"Xia","year":"2018","journal-title":"Environ. Sci. Process. Impacts"},{"issue":"1","key":"10.1016\/j.envres.2026.125714_bib46","first-page":"184","article-title":"Spatial-temporal variations and driving factors analysis of total nitrogen concentration in the Haihe River basin from 2018 to 2022","volume":"46","author":"Xiong","year":"2025","journal-title":"Environmental Science"},{"issue":"1","key":"10.1016\/j.envres.2026.125714_bib47","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1038\/s41467-025-57442-0","article-title":"Coupling nitrogen removal and watershed management to improve global lake water quality","volume":"16","author":"Yan","year":"2025","journal-title":"Nat. Commun."},{"issue":"1","key":"10.1016\/j.envres.2026.125714_bib48","doi-asserted-by":"crossref","first-page":"159","DOI":"10.3390\/jmse12010159","article-title":"A comprehensive review of machine learning for water quality prediction over the past five years","volume":"12","author":"Yan","year":"2024","journal-title":"J. Mar. Sci. Eng."},{"issue":"59","key":"10.1016\/j.envres.2026.125714_bib49","doi-asserted-by":"crossref","first-page":"124316","DOI":"10.1007\/s11356-023-30774-4","article-title":"Forecasting water quality variable using deep learning and weighted averaging ensemble models","volume":"30","author":"Zamani","year":"2023","journal-title":"Environ. Sci. Pollut. Control Ser."},{"issue":"9","key":"10.1016\/j.envres.2026.125714_bib50","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"37","author":"Zeng","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"12","key":"10.1016\/j.envres.2026.125714_bib51","doi-asserted-by":"crossref","first-page":"5308","DOI":"10.1021\/acs.chemrev.9b00613","article-title":"Global nitrogen cycle: critical enzymes, organisms, and processes for nitrogen budgets and dynamics","volume":"120","author":"Zhang","year":"2020","journal-title":"Chem. Rev."},{"issue":"3","key":"10.1016\/j.envres.2026.125714_bib52","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1038\/s44221-024-00202-z","article-title":"Deep learning for water quality","volume":"2","author":"Zhi","year":"2024","journal-title":"Nat. Water"},{"issue":"12","key":"10.1016\/j.envres.2026.125714_bib53","first-page":"11106","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.envres.2026.125714_bib54","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhydrol.2020.125164","article-title":"Real-time probabilistic forecasting of river water quality under data missing situation: deep learning plus post-processing techniques","volume":"589","author":"Zhou","year":"2020","journal-title":"J. Hydrol."}],"container-title":["Environmental Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0013935126020451?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0013935126020451?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:29:14Z","timestamp":1792052954000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0013935126020451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":54,"alternative-id":["S0013935126020451"],"URL":"https:\/\/doi.org\/10.1016\/j.envres.2026.125714","relation":{},"ISSN":["0013-9351"],"issn-type":[{"value":"0013-9351","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A physically constrained deep learning framework for total nitrogen prediction: A case study of a reservoir in North China","name":"articletitle","label":"Article Title"},{"value":"Environmental Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.envres.2026.125714","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"125714"}}