{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T01:03:02Z","timestamp":1790643782233,"version":"4.1.0"},"reference-count":86,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":23,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100007268","name":"Washington University in St. Louis","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["113\u20102917\u2010I\u2010564\u2010012"],"award-info":[{"award-number":["113\u20102917\u2010I\u2010564\u2010012"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Water Environment Research"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Target variable selection is often predefined in machine learning (ML)\u2013based surface water pollution prediction without systematically considering dataset characteristics. This study developed a target variable selection unit (TVSU) integrating Gini feature importance and model pre\u2010evaluation for same\u2010period, cross\u2010station, and cross\u2010variable reconstruction of surface water quality and associated pollution\u2010management decision support. Results showed that the scenario adhering to TVSU achieved the best predictive performance in both shallow and deep learning models (nRMSE values of 0.418 and 0.295\/relative MAE values of 36.4% and 30.4%), whereas scenarios disregarding TVSU exhibited substantially higher prediction errors. Post hoc interpretation analyses further demonstrated that TVSU enabled clearer identification of key pollution\u2010related variables. The proposed approach also provided flexibility for evaluating different pollution indicators and monitoring stations under multiple management scenarios. From a practical perspective, the workflow can help researchers and monitoring agencies prioritize candidate water\u2010quality variables and monitoring stations before model development, thereby supporting more transparent and management\u2010relevant environmental ML design. Overall, this study highlights the importance of systematic target variable selection for improving the reliability and applicability of environmental ML models in water quality management.<\/jats:p>","DOI":"10.1002\/wer.70588","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T09:50:02Z","timestamp":1790243402000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Target Variable Selection Into Environmental Machine Learning for Surface Water Pollution Management"],"prefix":"10.1002","volume":"98","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5721-7791","authenticated-orcid":false,"given":"Chao\u2010Chin","family":"Chang","sequence":"first","affiliation":[{"name":"Department of Safety, Health and Environmental Engineering National Kaohsiung University of Science and Technology  Kaohsiung Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6302-6556","authenticated-orcid":false,"given":"Zhen","family":"He","sequence":"additional","affiliation":[{"name":"Department of Energy, Environmental and Chemical Engineering Washington University in St. Louis  St. Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.2175\/106143016X14696400495497"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jwpe.2024.104789"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11157-021-09592-y"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-019-05801-y"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.25156\/ptj.v12n1y2022.pp21-29"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/713827181"},{"key":"e_1_2_10_9_1","unstructured":"Bay Y. Y. andK. A.Yearick.2024. \u201cMachine Learning vs Deep Learning: The Generalization Problem.\u201d arXiv Preprint arXiv:2403.01621."},{"issue":"2","key":"e_1_2_10_10_1","first-page":"281","article-title":"Random Search for Hyper\u2010Parameter Optimization","volume":"13","author":"Bergstra J.","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.077"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4076(96)01818-0"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-7-1247-2014"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2007.04.012"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2022.128340"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.115454"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"Chen T. andC.Guestrin.2016. \u201cXgboost: A Scalable Tree Boosting System.\u201d Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785\u2011794.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2024.122999"},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"Chu X. I. F.Ilyas S.Krishnan andJ.Wang.2016. \u201cData Cleaning: Overview and Emerging Challenges.\u201d Proceedings of the 2016 International Conference on Management of Data 2201\u20112206.","DOI":"10.1145\/2882903.2912574"},{"key":"e_1_2_10_21_1","unstructured":"Chung Y. P. J.Haas E.Upfal andT.Kraska.2018. \u201cUnknown Examples & Machine Learning Model Generalization.\u201d arXiv Preprint arXiv:1808.08294."},{"issue":"66561","key":"e_1_2_10_22_1","first-page":"10","article-title":"Impact of Wastewater on Surface Water Quality in Developing Countries: A Case Study of South Africa","volume":"10","author":"Edokpayi J. N.","year":"2017","journal-title":"Water Quality"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00516-9"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1061\/JHTRBP.HZENG-1401"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6226-1"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2017.02.024"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322753616"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"Hochreiter S.1997. \u201cLong Short\u2010Term Memory.\u201d Neural Computation MIT\u2010Press.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.3934\/environsci.2017.5.690"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2023.120037"},{"key":"e_1_2_10_33_1","unstructured":"Ke G. Q.Meng T.Finley et\u00a0al.2017. \u201cLightgbm: A Highly Efficient Gradient Boosting Decision Tree.\u201d Advances in Neural Information Processing Systems 30."},{"key":"e_1_2_10_34_1","unstructured":"Kohavi R.1995. \u201cA Study of Cross\u2010Validation and Bootstrap for Accuracy Estimation and Model Selection.\u201d In IJCAI (Vol. 14 no. 2 1137\u20111145."},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosust.2016.11.014"},{"key":"e_1_2_10_36_1","volume-title":"Water Treatment and Pathogen Control","author":"LeChevallier M. W.","year":"2004"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10661-016-5251-1"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/10408347.2017.1370670"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2020.126673"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2017.02465"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envpol.2017.08.114"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envres.2022.114723"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6054-2_7"},{"key":"e_1_2_10_44_1","unstructured":"Lundberg S.2017. \u201cA Unified Approach to Interpreting Model Predictions.\u201d arXiv Preprint arXiv:1705.07874."},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.34133\/olar.0050"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.115350"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-213"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22756-2"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40899-024-01188-y"},{"key":"e_1_2_10_50_1","volume-title":"Interpretable Machine Learning","author":"Molnar C.","year":"2020"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/78.3.691"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10661-019-7446-8"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty373"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.2166\/aqua.2023.005"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1080\/21622515.2022.2118084"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.115349"},{"key":"e_1_2_10_57_1","first-page":"3","volume-title":"Models, Reasoning and Inference","author":"Pearl J.","year":"2000"},{"key":"e_1_2_10_58_1","doi-asserted-by":"crossref","unstructured":"Piri I. I.Homayoonnezhad andP.Amirian.2010. \u201cInvestigation on Optimization of Conventional Drinking Water Treatment Plant.\u201d 2010 2nd International Conference on Chemical Biological and Environmental Engineering 304 310 IEEE.","DOI":"10.1109\/ICBEE.2010.5652523"},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1301"},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022643204877"},{"key":"e_1_2_10_61_1","doi-asserted-by":"crossref","unstructured":"Ribeiro M. T. S.Singh andC.Guestrin.2016. \u201c\u201cWhy Should I Trust You?\u201d Explaining the Predictions of Any Classifier.\u201d Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135\u20111144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-021-04148-9"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186008X344522"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000002864"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-020-11490-9"},{"key":"e_1_2_10_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.12691\/ajams-8-2-1"},{"key":"e_1_2_10_68_1","volume-title":"Natural Organic Matter in Water: Characterization and Treatment Methods","author":"Sillanp\u00e4\u00e4 M.","year":"2014"},{"key":"e_1_2_10_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemosphere.2017.09.113"},{"key":"e_1_2_10_70_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:STCO.0000035301.49549.88"},{"key":"e_1_2_10_71_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci034160g"},{"key":"e_1_2_10_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2017.08.192"},{"key":"e_1_2_10_73_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.6.520"},{"key":"e_1_2_10_74_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27509-9"},{"key":"e_1_2_10_75_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91"},{"key":"e_1_2_10_76_1","doi-asserted-by":"publisher","DOI":"10.2166\/ws.2008.068"},{"key":"e_1_2_10_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-023-26611-3"},{"key":"e_1_2_10_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-013-1874-8"},{"key":"e_1_2_10_79_1","doi-asserted-by":"publisher","DOI":"10.3354\/cr030079"},{"key":"e_1_2_10_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11269-022-03126-z"},{"key":"e_1_2_10_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106829"},{"key":"e_1_2_10_82_1","unstructured":"Ying Z. D.Bourgeois J.You M.Zitnik andJ.Leskovec.2019. \u201cGnnexplainer: Generating Explanations for Graph Neural Networks.\u201d Advances in Neural Information Processing Systems 32."},{"key":"e_1_2_10_83_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhydene.2024.01.308"},{"key":"e_1_2_10_84_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2019.114888"},{"key":"e_1_2_10_85_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.09.033"},{"key":"e_1_2_10_86_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"e_1_2_10_87_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9122534"}],"container-title":["Water Environment Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/wer.70588","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/wer.70588","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/wer.70588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:45:37Z","timestamp":1790642737000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/wer.70588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":86,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/wer.70588"],"URL":"https:\/\/doi.org\/10.1002\/wer.70588","archive":["Portico"],"relation":{},"ISSN":["1061-4303","1554-7531"],"issn-type":[{"value":"1061-4303","type":"print"},{"value":"1554-7531","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"2026-05-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70588"}}