{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:44:52Z","timestamp":1792784692097,"version":"4.5.0"},"reference-count":140,"publisher":"American Chemical Society (ACS)","issue":"36","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["52330001"],"award-info":[{"award-number":["52330001"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep learning (DL) and related data-driven models are increasingly being used to predict membrane performance, guide material discovery, and optimize membrane processes. However, membrane separation is governed by coupled effects of material structure, solute properties, interfacial interactions, transport mechanisms, and operating conditions, making purely data-driven prediction difficult to generalize across membrane systems and water matrices. This review examines data\u2013mechanism fusion as a membrane-science-oriented framework that integrates experimental data, molecular simulations, material databases, imaging information, process time-series data, and physicochemical knowledge throughout the modeling workflow. We first summarize membrane data types and assess how feedforward, convolutional, graph-based, recurrent, Transformer, and hybrid architectures align with data modalities and tasks. We then review recent progress in ion-selective separation, micropollutant and emerging contaminant removal, membrane material screening and inverse design, fouling diagnosis, and operational optimization. Particular attention is given to how mechanistic descriptors, physical constraints, hybrid coupling, simulation-informed surrogates, and closed-loop learning improve model reliability and interpretability. Finally, we discuss persistent challenges, including data scarcity, data set heterogeneity, limited transferability, uncertainty quantification, weak physical interpretability, and the gap between computational prediction and experimental or pilot-scale validation. This review highlights data\u2013mechanism fusion as a practical route toward more reliable, interpretable, and adaptive membrane research workflows.<\/jats:p>","DOI":"10.1021\/acs.est.6c07517","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T01:31:14Z","timestamp":1788312674000},"page":"25088-25109","source":"Crossref","is-referenced-by-count":1,"title":["Data\u2013Mechanism\nFusion for Deep Learning-Enabled\nMembrane Performance Prediction and Material Discovery"],"prefix":"10.1021","volume":"60","author":[{"given":"Hai","family":"Liang","sequence":"first","affiliation":[{"name":"Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences , , ,","place":["Beijing, China, 100085"]},{"name":"Nanjing University , , 163 Xianlin Avenue, Qixia District , , ,","place":["Nanjing, Jiangsu, China, 210023"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiali","family":"Li","sequence":"additional","affiliation":[{"name":"Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences , , ,","place":["Beijing, China, 100085"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-835X","authenticated-orcid":true,"given":"Chengzhi","family":"Hu","sequence":"additional","affiliation":[{"name":"Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences , , ,","place":["Beijing, China, 100085"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"issue":"10","key":"2026091511122130200_cit1","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/s44221-024-00314-6","article-title":"Direct-drive photovoltaic electrodialysis\nvia flow-commanded current control [J]","volume":"2","author":"BESSETTE","year":"2024","journal-title":"Nature\nWater"},{"issue":"11","key":"2026091511122130200_cit2","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1038\/s44221-024-00327-1","article-title":"Analysis of energy,\nwater, land and cost implications of zero and minimal liquid discharge\ndesalination technologies [J]","volume":"2","author":"O\u2019CONNELL","year":"2024","journal-title":"Nature Water"},{"issue":"3","key":"2026091511122130200_cit3","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s44221-025-00398-8","article-title":"Solution-processable\npolymer membranes with hydrophilic subnanometre pores for sustainable\nlithium extraction [J]","volume":"3","author":"YANG","year":"2025","journal-title":"Nature Water"},{"issue":"11","key":"2026091511122130200_cit4","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1038\/s44221-024-00326-2","article-title":"Spontaneous lithium extraction and enrichment\nfrom brine with net energy output driven by counter-ion gradients\n[J]","volume":"2","author":"ZHANG","year":"2024","journal-title":"Nature Water"},{"issue":"7","key":"2026091511122130200_cit5","doi-asserted-by":"publisher","first-page":"3552","DOI":"10.1021\/acs.est.3c08956","article-title":"Membrane Design Principles\nfor Ion-Selective Electrodialysis: An\nAnalysis for Li\/Mg Separation","volume":"58","author":"WANG","year":"2024","journal-title":"Environ. Sci.\nTechnol."},{"issue":"6","key":"2026091511122130200_cit6","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1038\/s44221-025-00440-9","article-title":"Nanofiltration membranes\nwith ultra-high negative charge density for enhanced anion sieving\nand removal of organic micropollutants [J]","volume":"3","author":"XU","year":"2025","journal-title":"Nature Water"},{"issue":"1","key":"2026091511122130200_cit7","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/s41467-024-48419-6","article-title":"Electrochemical-repaired\nporous graphene membranes for precise ion-ion separation [J]","volume":"15","author":"ZHOU","year":"2024","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091511122130200_cit8","doi-asserted-by":"publisher","first-page":"3160","DOI":"10.1038\/s41467-024-47083-0","article-title":"Precision\nion separation via self-assembled channels [J]","volume":"15","author":"Hong","year":"2024","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091511122130200_cit9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/s41545-024-00322-9","article-title":"Effect of solution ions\non the charge and performance of nanofiltration membranes [J]","volume":"7","author":"ROTH","year":"2024","journal-title":"npj Clean Water"},{"issue":"9","key":"2026091511122130200_cit10","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1038\/s44221-025-00498-5","article-title":"Impact of charge homogeneity\non ion selectivity in polyamide membranes [J]","volume":"3","author":"LU","year":"2025","journal-title":"Nature Water"},{"issue":"33","key":"2026091511122130200_cit11","doi-asserted-by":"publisher","first-page":"21633","DOI":"10.1021\/acsnano.4c00540","article-title":"Ion\u2013Ion Selectivity\nof Synthetic Membranes with Confined Nanostructures [J]","volume":"18","author":"LIU","year":"2024","journal-title":"ACS Nano"},{"issue":"35","key":"2026091511122130200_cit12","doi-asserted-by":"publisher","first-page":"15874","DOI":"10.1021\/acs.est.4c07510","article-title":"The Hidden Role of the Dielectric Effect in\nNanofiltration: A Novel Perspective to Unravel New Ion Separation\nMechanisms [J]","volume":"58","author":"ZHAI","year":"2024","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit13","doi-asserted-by":"publisher","first-page":"124925","DOI":"10.1016\/j.memsci.2025.124925","article-title":"A physics-informed machine learning framework\nfor understanding the rejection mechanism of hydrophilic micropollutants\nin polyamide membranes [J]","volume":"740","author":"ZHAO","year":"2026","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit14","doi-asserted-by":"publisher","first-page":"122927","DOI":"10.1016\/j.memsci.2024.122927","article-title":"Molecular\nfingerprint-aided prediction\nof organic solute rejection in reverse osmosis and nanofiltration\n[J]","volume":"705","author":"LEE","year":"2024","journal-title":"J. Membr. Sci."},{"issue":"13","key":"2026091511122130200_cit15","doi-asserted-by":"publisher","first-page":"5878","DOI":"10.1021\/acs.est.3c08523","article-title":"Understanding\nRejection\nMechanisms of Trace Organic Contaminants by Polyamide Membranes via\nData-Knowledge Codriven Machine Learning [J]","volume":"58","author":"WANG","year":"2024","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit16","doi-asserted-by":"publisher","first-page":"116748","DOI":"10.1016\/j.desal.2023.116748","article-title":"Ensemble machine learning reveals key structural\nand operational features governing ion selectivity of polyamide nanofiltration\nmembranes [J]","volume":"564","author":"LU","year":"2023","journal-title":"Desalination"},{"key":"2026091511122130200_cit17","doi-asserted-by":"publisher","first-page":"124648","DOI":"10.1016\/j.memsci.2025.124648","article-title":"DMGTNet:\nA graph-temporal deep learning model\nfor membrane fouling prediction in dual-membrane wastewater treatment\nsystems [J]","volume":"736","author":"ZHANG","year":"2025","journal-title":"J. Membr. Sci."},{"issue":"20","key":"2026091511122130200_cit18","doi-asserted-by":"publisher","first-page":"10010","DOI":"10.1021\/acs.est.4c12835","article-title":"Predicting Membrane\nFouling of Submerged Membrane Bioreactor Wastewater Treatment Plants\nUsing Machine Learning [J]","volume":"59","author":"ZHU","year":"2025","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit19","doi-asserted-by":"publisher","first-page":"124133","DOI":"10.1016\/j.memsci.2025.124133","article-title":"Development of physics-informed machine-learning models\nto enhance understanding and prediction of membrane fouling [J]","volume":"728","author":"GARAKANI","year":"2025","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit20","doi-asserted-by":"publisher","first-page":"125024","DOI":"10.1016\/j.memsci.2025.125024","article-title":"Molecular structure-based machine learning\nreveals rejection mechanisms of emerging contaminants by polyamide\nmembranes [J]","volume":"741","author":"MA","year":"2026","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit21","doi-asserted-by":"publisher","first-page":"125449","DOI":"10.1016\/j.watres.2026.125449","article-title":"Physics-informed neural\nnetworks in water and wastewater systems: a critical review [J]","volume":"293","author":"BELLA","year":"2026","journal-title":"Water Res."},{"issue":"46","key":"2026091511122130200_cit22","doi-asserted-by":"publisher","first-page":"17851","DOI":"10.1021\/acs.est.2c08384","article-title":"Exploring the Knowledge\nAttained by Machine Learning on Ion Transport across Polyamide Membranes\nUsing Explainable Artificial Intelligence [J]","volume":"57","author":"JEONG","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit23","doi-asserted-by":"publisher","first-page":"123256","DOI":"10.1016\/j.memsci.2024.123256","article-title":"Machine learning for\nthe advancement of membrane science and technology: A critical review\n[J]","volume":"713","author":"IGNACZ","year":"2025","journal-title":"J. Membr. Sci."},{"issue":"10","key":"2026091511122130200_cit24","doi-asserted-by":"publisher","first-page":"2953","DOI":"10.1021\/acs.nanolett.3c05137","article-title":"Machine Learning in Membrane Design: From Property Prediction to\nAI-Guided Optimization [J]","volume":"24","author":"Cao","year":"2024","journal-title":"Nano Lett."},{"key":"2026091511122130200_cit25","doi-asserted-by":"publisher","first-page":"125203","DOI":"10.1016\/j.apenergy.2024.125203","article-title":"A systematic review\nof recent advances in the application of machine learning in membrane-based\ngas separation technologies [J]","volume":"381","author":"ABDOLLAHI","year":"2025","journal-title":"Applied Energy"},{"key":"2026091511122130200_cit26","doi-asserted-by":"publisher","first-page":"137332","DOI":"10.1016\/j.seppur.2026.137332","article-title":"Next-generation\npolymeric membranes for CO2 separation:\nMechanistic frontiers, sustainable pathways, and intelligent design\n[J]","volume":"394","author":"GOSWAMI","year":"2026","journal-title":"Sep. Purif. Technol."},{"issue":"4","key":"2026091511122130200_cit27","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41893-026-01766-2","article-title":"Intelligent fouling\nmonitoring in membrane-based wastewater treatment [J]","volume":"9","author":"LAI","year":"2026","journal-title":"Nature Sustainability"},{"key":"2026091511122130200_cit28","doi-asserted-by":"publisher","first-page":"118299","DOI":"10.1016\/j.watres.2022.118299","article-title":"Artificial intelligence-incorporated membrane\nfouling prediction for membrane-based processes in the past 20 years:\nA critical review [J]","volume":"216","author":"NIU","year":"2022","journal-title":"Water Res."},{"issue":"2","key":"2026091511122130200_cit29","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/s10311-023-01695-y","article-title":"Machine learning for\nmembrane design in energy production, gas separation, and water treatment:\na review [J]","volume":"22","author":"OSMAN","year":"2024","journal-title":"Environmental chemistry letters"},{"issue":"1","key":"2026091511122130200_cit30","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.gee.2022.12.001","article-title":"Machine learning for membrane design and discovery\n[J]","volume":"9","author":"YIN","year":"2024","journal-title":"Green Energy & Environment"},{"issue":"2","key":"2026091511122130200_cit31","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1038\/s41563-025-02403-7","article-title":"Artificial intelligence-driven\napproaches for materials design and discovery [J]","volume":"25","author":"CHENG","year":"2026","journal-title":"Nat. Mater."},{"key":"2026091511122130200_cit32","doi-asserted-by":"publisher","first-page":"100072","DOI":"10.1016\/j.advmem.2023.100072","article-title":"Machine\nlearning toward improving the performance\nof membrane-based wastewater treatment: A review [J]","volume":"3","author":"DANSAWAD","year":"2023","journal-title":"Advanced Membranes"},{"key":"2026091511122130200_cit33","doi-asserted-by":"publisher","first-page":"106532","DOI":"10.1016\/j.jwpe.2024.106532","article-title":"Applications of artificial intelligence\nfor membrane separation: A review [J]","volume":"68","author":"JAFARI","year":"2024","journal-title":"Journal\nof Water Process Engineering"},{"key":"2026091511122130200_cit34","doi-asserted-by":"publisher","first-page":"133091","DOI":"10.1016\/j.seppur.2025.133091","article-title":"Machine learning in membrane science: Bridging\nmaterials, structures, and performance for next-generation membrane\ndesign [J]","volume":"369","author":"LIANG","year":"2025","journal-title":"Sep. Purif. Technol."},{"key":"2026091511122130200_cit35","doi-asserted-by":"publisher","first-page":"100374","DOI":"10.1016\/j.ccst.2025.100374","article-title":"Machine learning-assisted development of gas\nseparation membranes: A review [J]","volume":"14","author":"LI","year":"2025","journal-title":"Carbon Capture\nScience & Technology"},{"issue":"7","key":"2026091511122130200_cit36","doi-asserted-by":"publisher","first-page":"102067","DOI":"10.1016\/j.xcrp.2024.102067","article-title":"Superior polymeric gas\nseparation membrane designed by explainable graph machine learning\n[J]","volume":"5","author":"XU","year":"2024","journal-title":"Cell Reports Physical Science"},{"key":"2026091511122130200_cit37","doi-asserted-by":"publisher","first-page":"123169","DOI":"10.1016\/j.memsci.2024.123169","article-title":"Machine learning-guided\ndiscovery of polymer membranes for CO2 separation with genetic algorithm\n[J]","volume":"712","author":"BASDOGAN","year":"2024","journal-title":"J. Membr. Sci."},{"issue":"29","key":"2026091511122130200_cit38","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abn9545","article-title":"Machine\nlearning enables interpretable discovery\nof innovative polymers for gas separation membranes [J]","volume":"8","author":"YANG","year":"2022","journal-title":"Science Advances"},{"issue":"24","key":"2026091511122130200_cit39","doi-asserted-by":"publisher","first-page":"9533","DOI":"10.1021\/acs.iecr.3c00636","article-title":"Determining Ion Activity Coefficients in Ion-Exchange Membranes with\nMachine Learning and Molecular Dynamics Simulations [J]","volume":"62","author":"Gallage Dona","year":"2023","journal-title":"Ind. Eng. Chem. Res."},{"issue":"16","key":"2026091511122130200_cit40","doi-asserted-by":"publisher","first-page":"11348","DOI":"10.1021\/acs.est.1c04041","article-title":"Predicting Micropollutant\nRemoval\nby Reverse Osmosis and Nanofiltration Membranes: Is Machine Learning\nViable? [J]","volume":"55","author":"JEONG","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit41","doi-asserted-by":"publisher","first-page":"159348","DOI":"10.1016\/j.scitotenv.2022.159348","article-title":"Prediction of organic\ncontaminant rejection by nanofiltration and reverse osmosis membranes\nusing interpretable machine learning models [J]","volume":"857","author":"ZHU","year":"2023","journal-title":"Science of The Total Environment"},{"issue":"46","key":"2026091511122130200_cit42","doi-asserted-by":"publisher","first-page":"17831","DOI":"10.1021\/acs.est.2c05404","article-title":"Understanding and Designing\na High-Performance Ultrafiltration Membrane Using Machine Learning\n[J]","volume":"57","author":"GAO","year":"2023","journal-title":"Environ. Sci. Technol."},{"issue":"46","key":"2026091511122130200_cit43","doi-asserted-by":"publisher","first-page":"17841","DOI":"10.1021\/acs.est.2c05571","article-title":"Machine Learning Guided Polyamide Membrane\nwith Exceptional Solute\u2013Solute Selectivity and Permeance [J]","volume":"57","author":"DENG","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"2026091511122130200_cit44","doi-asserted-by":"publisher","first-page":"116293","DOI":"10.1016\/j.desal.2022.116293","article-title":"Revealing key structural and operating features\non water\/salts selectivity of polyamide nanofiltration membranes by\nensemble machine learning [J]","volume":"548","author":"MA","year":"2023","journal-title":"Desalination"},{"issue":"D1","key":"2026091511122130200_cit45","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"PubChem 2023 update\n[J]","volume":"51","author":"KIM","year":"2023","journal-title":"Nucleic Acids Res."},{"issue":"6","key":"2026091511122130200_cit46","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1039\/D3DD00153A","article-title":"A database of molecular\nproperties integrated in the Materials Project [J]","volume":"2","author":"SPOTTE-SMITH","year":"2023","journal-title":"Digital Discovery"},{"issue":"1","key":"2026091511122130200_cit47","doi-asserted-by":"publisher","first-page":"4931","DOI":"10.1038\/s41467-023-40257-2","article-title":"Data-driven predictions\nof complex organic mixture permeation in polymer membranes [J]","volume":"14","author":"LEE","year":"2023","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091511122130200_cit48","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41524-024-01373-9","article-title":"Gas permeability,\ndiffusivity,\nand solubility in polymers: Simulation-experiment data fusion and\nmulti-task machine learning [J]","volume":"10","author":"PHAN","year":"2024","journal-title":"npj Computational\nMaterials"},{"issue":"6","key":"2026091511122130200_cit49","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1515\/polyeng-2019-0329","article-title":"Polymer genome\u2013based\nprediction of gas permeabilities in polymers [J]","volume":"40","author":"ZHU","year":"2020","journal-title":"Journal of Polymer Engineering"},{"key":"2026091511122130200_cit50","doi-asserted-by":"publisher","first-page":"122563","DOI":"10.1016\/j.memsci.2024.122563","article-title":"Machine learning-based\ndiscovery of molecular descriptors that control polymer gas permeation\n[J]","volume":"697","author":"SHASTRY","year":"2024","journal-title":"J. Membr. Sci."},{"issue":"1","key":"2026091511122130200_cit51","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests\n[J]","volume":"45","author":"BREIMAN","year":"2001","journal-title":"Machine Learning"},{"issue":"3","key":"2026091511122130200_cit52","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"CORTES","year":"1995","journal-title":"Machine\nLearning"},{"key":"2026091511122130200_cit53","doi-asserted-by":"crossref","unstructured":"CHEN, T.; GUESTRIN, C.\n          XGBoost: A Scalable\nTree Boosting System [Z].  Proceedings of the\n22nd ACM SIGKDD International Conference on Knowledge Discovery and\nData Mining; Association for Computing Machinery: 2016, 785\u201394. 10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"2026091511122130200_cit54","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning\n[J]","volume":"6","author":"SHORTEN","year":"2019","journal-title":"Journal of Big Data"},{"issue":"1","key":"2026091511122130200_cit55","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","article-title":"Mordred: a molecular\ndescriptor calculator [J]","volume":"10","author":"MORIWAKI","year":"2018","journal-title":"Journal of Cheminformatics"},{"key":"2026091511122130200_cit56","unstructured":"DUVENAUD, D.; MACLAURIN, D.; AGUILERA-IPARRAGUIRRE, J.; et al., Convolutional networks on graphs for\nlearning molecular fingerprints\n[Z].  Proceedings of the 29th International\nConference on Neural Information Processing Systems - Volume 2; MIT Press: 2015, 2224\u201332."},{"key":"2026091511122130200_cit57","unstructured":"GILMER, J.; SCHOENHOLZ, S. S.; RILEY, P. F.; et al., Neural message passing for Quantum chemistry [Z].  Proceedings of the 34th International Conference on Machine Learning\n- Volume 70; JMLR.org: 2017, pp 1263\u201372."},{"key":"2026091511122130200_cit58","doi-asserted-by":"crossref","unstructured":"ZERVEAS, G.; JAYARAMAN, S.; PATEL, D.; et al., A Transformer-based\nFramework for Multivariate Time Series Representation Learning [Z].  Proceedings of the 27th ACM SIGKDD Conference on Knowledge\nDiscovery & Data Mining. Association\nfor Computing Machinery: 2021; pp 2114\u201324. 10.1145\/3447548.3467401.","DOI":"10.1145\/3447548.3467401"},{"issue":"4","key":"2026091511122130200_cit59","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers\nfor interpretable multi-horizon time series forecasting [J]","volume":"37","author":"LIM","year":"2021","journal-title":"International Journal of Forecasting"},{"key":"2026091511122130200_cit60","unstructured":"VASWANI, A.; SHAZEER, N.; PARMAR, N.; et al., Attention is all you need [Z].  Proceedings\nof the 31st International Conference on Neural Information Processing\nSystems; Curran Associates Inc: 2017; pp 6000\u201310."},{"key":"2026091511122130200_cit61","doi-asserted-by":"publisher","first-page":"112896","DOI":"10.1016\/j.eswa.2019.112896","article-title":"Forecasting\nacross time series databases\nusing recurrent neural networks on groups of similar series: A clustering\napproach [J]","volume":"140","author":"BANDARA","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"2026091511122130200_cit62","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term\nMemory [J]","volume":"9","author":"HOCHREITER","year":"1997","journal-title":"Neural\nComputation"},{"key":"2026091511122130200_cit63","doi-asserted-by":"publisher","first-page":"117854","DOI":"10.1016\/j.desal.2024.117854","article-title":"Predicting\nthe boron removal of reverse osmosis membranes using machine learning\n[J]","volume":"586","author":"Sukarno","year":"2024","journal-title":"Desalination"},{"key":"2026091511122130200_cit64","doi-asserted-by":"publisher","first-page":"122363","DOI":"10.1016\/j.watres.2024.122363","article-title":"Machine\nlearning models\nfor predicting the rejection of organic pollutants by forward osmosis\nand reverse osmosis membranes and unveiling the rejection mechanisms\n[J]","volume":"266","author":"TAYARA","year":"2024","journal-title":"Water Res."},{"key":"2026091511122130200_cit65","doi-asserted-by":"publisher","first-page":"169164","DOI":"10.1016\/j.scitotenv.2023.169164","article-title":"Predictive modeling based on artificial\nneural networks for membrane\nfouling in a large pilot-scale anaerobic membrane bioreactor for treating\nreal municipal wastewater [J]","volume":"912","author":"WANG","year":"2024","journal-title":"Science of The\nTotal Environment"},{"issue":"2","key":"2026091511122130200_cit66","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abl5771","article-title":"Machine learning reveals key ion selectivity\nmechanisms in polymeric membranes with subnanometer pores [J]","volume":"8","author":"RITT","year":"2022","journal-title":"Science Advances"},{"issue":"3","key":"2026091511122130200_cit67","doi-asserted-by":"publisher","first-page":"107649","DOI":"10.1016\/j.jece.2022.107649","article-title":"Research on the membrane\nfouling diagnosis of MBR membrane module based on ECA-CNN [J]","volume":"10","author":"SHI","year":"2022","journal-title":"Journal of Environmental Chemical Engineering"},{"issue":"15","key":"2026091511122130200_cit68","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e35358","article-title":"Geometric feature extraction\nin nanofiber membrane image based on convolution neural network for\nsurface roughness prediction [J]","volume":"10","author":"KANG","year":"2024","journal-title":"Heliyon"},{"key":"2026091511122130200_cit69","doi-asserted-by":"publisher","first-page":"121959","DOI":"10.1016\/j.seppur.2022.121959","article-title":"A deep neural networks\nframework for in-situ biofilm thickness detection and hydrodynamics\ntracing for filtration systems [J]","volume":"301","author":"QAMAR","year":"2022","journal-title":"Sep. Purif.\nTechnol."},{"issue":"1","key":"2026091511122130200_cit70","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41545-025-00451-9","article-title":"Precise biofilm thickness\nprediction in SWRO desalination from planar camera images by DNN models\n[J]","volume":"8","author":"TANUDJAJA","year":"2025","journal-title":"npj Clean Water"},{"key":"2026091511122130200_cit71","doi-asserted-by":"publisher","first-page":"122291","DOI":"10.1016\/j.memsci.2023.122291","article-title":"Noninvasive monitoring\nof fouling in membrane processes by optical coherence tomography:\nA review [J]","volume":"692","author":"HUISMAN","year":"2024","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit72","doi-asserted-by":"publisher","first-page":"1426145","DOI":"10.3389\/frmst.2024.1426145","article-title":"A review on microfiltration membranes: fabrication,\nphysical morphology, and fouling characterization techniques [J]","volume":"3","author":"ALSOY ALTINKAYA","year":"2024","journal-title":"Frontiers in Membrane Science and Technology"},{"key":"2026091511122130200_cit73","doi-asserted-by":"publisher","first-page":"117353","DOI":"10.1016\/j.desal.2024.117353","article-title":"Prediction of reverse\nosmosis membrane fouling in water reuse by\nintegrated adsorption and data-driven models [J]","volume":"576","author":"TENG","year":"2024","journal-title":"Desalination"},{"issue":"1","key":"2026091511122130200_cit74","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1039\/D5DD00272A","article-title":"PolyRL: reinforcement learning-guided polymer\ngeneration for multi-objective polymer discovery [J]","volume":"5","author":"LI","year":"2026","journal-title":"Digital Discovery"},{"issue":"1","key":"2026091511122130200_cit75","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.memsci.2009.06.048","article-title":"Artificial neural network\nmodels based on QSAR for predicting rejection of neutral organic compounds\nby polyamide nanofiltration and reverse osmosis membranes [J]","volume":"342","author":"YANGALI-QUINTANILLA","year":"2009","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit76","doi-asserted-by":"publisher","first-page":"128960","DOI":"10.1016\/j.seppur.2024.128960","article-title":"Machine learning-assisted\nperformance prediction from the synthesis conditions of nanofiltration\nmembranes [J]","volume":"354","author":"SUTARIYA","year":"2025","journal-title":"Sep. Purif. Technol."},{"key":"2026091511122130200_cit77","doi-asserted-by":"publisher","first-page":"117164","DOI":"10.1016\/j.memsci.2019.06.004","article-title":"Deep neural networks\nfor modeling fouling growth and flux decline during NF\/RO membrane\nfiltration [J]","volume":"587","author":"PARK","year":"2019","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit78","doi-asserted-by":"publisher","first-page":"117070","DOI":"10.1016\/j.watres.2021.117070","article-title":"Deep learning\nmodel for simulating\ninfluence of natural organic matter in nanofiltration [J]","volume":"197","author":"SHIM","year":"2021","journal-title":"Water Res."},{"key":"2026091511122130200_cit79","doi-asserted-by":"publisher","first-page":"108539","DOI":"10.1016\/j.jwpe.2025.108539","article-title":"AI-driven multivariate\ntime series forecasting of transmembrane pressure in ultrafiltration:\nA stationarity-aware approach [J]","volume":"77","author":"KIM","year":"2025","journal-title":"Journal of\nWater Process Engineering"},{"key":"2026091511122130200_cit80","unstructured":"REHMAN, D.; LIENHARD, J. H.\n          Physics-constrained\nneural differential equations for learning multi-ionic transport [J].  arXiv, 2023."},{"key":"2026091511122130200_cit81","doi-asserted-by":"publisher","first-page":"124140","DOI":"10.1016\/j.watres.2025.124140","article-title":"Predicting and understanding\nthe performance of polyamide nanofiltration membrane for Li\/Mg selective\nseparation based on machine learning [J]","volume":"285","author":"SUN","year":"2025","journal-title":"Water\nRes."},{"issue":"10","key":"2026091511122130200_cit82","doi-asserted-by":"publisher","first-page":"4684","DOI":"10.1021\/acs.jcim.0c00726","article-title":"PI1M: A Benchmark Database\nfor Polymer Informatics [J]","volume":"60","author":"MA","year":"2020","journal-title":"J. Chem. Inf. Model."},{"issue":"9","key":"2026091511122130200_cit83","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1021\/acscentsci.9b00476","article-title":"BigSMILES: A Structurally-Based\nLine Notation for Describing Macromolecules [J]","volume":"5","author":"LIN","year":"2019","journal-title":"ACS Central Science"},{"issue":"4","key":"2026091511122130200_cit84","doi-asserted-by":"publisher","first-page":"045024","DOI":"10.1088\/2632-2153\/aba947","article-title":"Self-referencing\nembedded\nstrings (SELFIES): A 100% robust molecular string representation [J]","volume":"1","author":"KRENN","year":"2020","journal-title":"Machine Learning: Science and Technology"},{"issue":"1","key":"2026091511122130200_cit85","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nchemical language and information system","volume":"28","author":"WEININGER","year":"1988","journal-title":"1.\nIntroduction to methodology and encoding rules [J]. Journal of Chemical\nInformation and Computer Sciences"},{"issue":"1","key":"2026091511122130200_cit86","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s41524-024-01466-5","article-title":"On-demand reverse\ndesign of polymers with PolyTAO [J]","volume":"10","author":"QIU","year":"2024","journal-title":"npj Computational\nMaterials"},{"issue":"1","key":"2026091511122130200_cit87","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1038\/s41524-023-01016-5","article-title":"TransPolymer: a Transformer-based\nlanguage model for polymer property predictions [J]","volume":"9","author":"XU","year":"2023","journal-title":"npj Computational Materials"},{"issue":"1","key":"2026091511122130200_cit88","doi-asserted-by":"publisher","first-page":"4099","DOI":"10.1038\/s41467-023-39868-6","article-title":"polyBERT: a chemical language model\nto enable fully\nmachine-driven ultrafast polymer informatics [J]","volume":"14","author":"KUENNETH","year":"2023","journal-title":"Nat. Commun."},{"issue":"31","key":"2026091511122130200_cit89","doi-asserted-by":"publisher","first-page":"17575","DOI":"10.1021\/acs.jpcc.8b02913","article-title":"Polymer Genome: A Data-Powered\nPolymer Informatics Platform for Property Predictions [J]","volume":"122","author":"KIM","year":"2018","journal-title":"J. Phys. Chem. C"},{"issue":"18","key":"2026091511122130200_cit90","doi-asserted-by":"publisher","first-page":"4729","DOI":"10.1016\/j.polymer.2013.05.075","article-title":"Energy-efficient polymeric\ngas separation membranes for a sustainable future: A review [J]","volume":"54","author":"SANDERS","year":"2013","journal-title":"Polymer"},{"key":"2026091511122130200_cit91","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.memsci.2018.03.051","article-title":"Selectivity\nof ion exchange membranes:\nA review [J]","volume":"555","author":"LUO","year":"2018","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit92","doi-asserted-by":"publisher","first-page":"123194","DOI":"10.1016\/j.ces.2025.123194","article-title":"Generative transformer\ndecoder-only model polyGT: Toward polymer informatics comprehension\nand target polymer inverse design [J]","volume":"324","author":"XU","year":"2026","journal-title":"Chem.\nEng. Sci."},{"issue":"1","key":"2026091511122130200_cit93","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s41524-023-01088-3","article-title":"AI powered, automated discovery of polymer\nmembranes for carbon capture [J]","volume":"9","author":"GIRO","year":"2023","journal-title":"npj Computational\nMaterials"},{"issue":"1","key":"2026091511122130200_cit94","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1038\/s41524-021-00650-1","article-title":"Atomistic Line Graph Neural Network for improved materials\nproperty predictions [J]","volume":"7","author":"CHOUDHARY","year":"2021","journal-title":"npj Computational\nMaterials"},{"issue":"9","key":"2026091511122130200_cit95","doi-asserted-by":"publisher","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","article-title":"Graph Networks as a Universal Machine Learning\nFramework for Molecules and Crystals [J]","volume":"31","author":"CHEN","year":"2019","journal-title":"Chem.\nMater."},{"issue":"14","key":"2026091511122130200_cit96","doi-asserted-by":"publisher","first-page":"145301","DOI":"10.1103\/PhysRevLett.120.145301","article-title":"Crystal Graph Convolutional Neural Networks for Accurate\nand Interpretable Prediction of Material Properties [J]","volume":"120","author":"XIE","year":"2018","journal-title":"Phys. Rev. Lett."},{"issue":"22","key":"2026091511122130200_cit97","doi-asserted-by":"publisher","first-page":"5446","DOI":"10.1021\/acs.jcim.2c00876","article-title":"Interpretable Graph\nTransformer Network for Predicting Adsorption Isotherms of Metal\u2013Organic\nFrameworks [J]","volume":"62","author":"CHEN","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026091511122130200_cit98","doi-asserted-by":"publisher","first-page":"111388","DOI":"10.1016\/j.commatsci.2022.111388","article-title":"Graph neural network\npredictions of metal organic framework CO2 adsorption properties [J]","volume":"210","author":"CHOUDHARY","year":"2022","journal-title":"Comput. Mater. Sci."},{"key":"2026091511122130200_cit99","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.eng.2025.08.012","article-title":"A Multi-Scale\nGraph Neural Network for the Prediction of Multi-Component\nGas Adsorption [J]","volume":"52","author":"LI","year":"2025","journal-title":"Engineering"},{"issue":"41","key":"2026091511122130200_cit100","doi-asserted-by":"publisher","first-page":"56366","DOI":"10.1021\/acsami.4c12198","article-title":"Graph Neural Networks for Carbon Dioxide Adsorption\nPrediction in\nAluminum-Substituted Zeolites [J]","volume":"16","author":"PETKOVIC\u0301","year":"2024","journal-title":"ACS Appl.\nMater. Interfaces"},{"issue":"18","key":"2026091511122130200_cit101","doi-asserted-by":"publisher","first-page":"21738","DOI":"10.1021\/acsami.2c04016","article-title":"High-Throughput Screening\nof COF Membranes and COF\/Polymer MMMs for Helium Separation and Hydrogen\nPurification [J]","volume":"14","author":"AYDIN","year":"2022","journal-title":"ACS Appl. Mater. Interfaces"},{"issue":"41","key":"2026091511122130200_cit102","doi-asserted-by":"publisher","first-page":"22577","DOI":"10.1021\/acs.jpcc.0c07062","article-title":"Computational\nSelection of High-Performing Covalent Organic Frameworks for Adsorption\nand Membrane-Based CO2\/H2 Separation [J]","volume":"124","author":"AKSU","year":"2020","journal-title":"J.\nPhys. Chem. C"},{"issue":"39","key":"2026091511122130200_cit103","doi-asserted-by":"publisher","first-page":"33693","DOI":"10.1021\/acsami.8b12746","article-title":"High-Throughput\nScreening\nof MOF Adsorbents and Membranes for H2 Purification and CO2 Capture\n[J]","volume":"10","author":"AVCI","year":"2018","journal-title":"ACS Appl. Mater. Interfaces"},{"issue":"30","key":"2026091511122130200_cit104","doi-asserted-by":"publisher","first-page":"17347","DOI":"10.1021\/acs.jpcc.8b05416","article-title":"Computational Screening of Metal-Organic\nFrameworks for Membrane-Based CO(2)\/N(2)\/H(2)O Separations: Best Materials\nfor Flue Gas Separation [J]","volume":"122","author":"DAGLAR","year":"2018","journal-title":"J. Phys. Chem.\nC Nanomater Interfaces"},{"issue":"38","key":"2026091511122130200_cit105","doi-asserted-by":"publisher","first-page":"2303447","DOI":"10.1002\/adfm.202303447","article-title":"Defect Engineering of\nMOF-Based Membrane for Gas Separation [J]","volume":"33","author":"LI","year":"2023","journal-title":"Adv.\nFunct. Mater."},{"issue":"16","key":"2026091511122130200_cit106","doi-asserted-by":"publisher","first-page":"6116","DOI":"10.1039\/C4CS00159A","article-title":"Metal\u2013organic framework membranes:\nfrom synthesis to separation application [J]","volume":"43","author":"QIU","year":"2014","journal-title":"Chem. Soc. Rev."},{"issue":"1","key":"2026091511122130200_cit107","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.gce.2020.11.004","article-title":"Design of metal-organic\nframework membranes towards\nultimate gas separation [J]","volume":"2","author":"SUN","year":"2021","journal-title":"Green Chemical\nEngineering"},{"key":"2026091511122130200_cit108","doi-asserted-by":"publisher","first-page":"120817","DOI":"10.1016\/j.memsci.2022.120817","article-title":"Membrane\nfouling prediction and uncertainty analysis using machine learning:\nA wastewater treatment plant case study [J]","volume":"660","author":"KOVACS","year":"2022","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit109","doi-asserted-by":"publisher","first-page":"2713","DOI":"10.4236\/jamp.2020.812201","article-title":"Deep Learning Based Model Predictive\nControl for a Reverse Osmosis Desalination Plant [J]","volume":"08","author":"KARIMANZIRA","year":"2020","journal-title":"Journal of Applied Mathematics and Physics"},{"key":"2026091511122130200_cit110","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-informed\nneural networks: A deep learning framework for solving forward and\ninverse problems involving nonlinear partial differential equations\n[J]","volume":"378","author":"RAISSI","year":"2019","journal-title":"J. Comput. Phys."},{"issue":"12","key":"2026091511122130200_cit111","doi-asserted-by":"publisher","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer:\nBeyond Efficient Transformer for Long Sequence Time-Series Forecasting\n[J]","volume":"35","author":"ZHOU","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial\nIntelligence"},{"key":"2026091511122130200_cit112","doi-asserted-by":"publisher","first-page":"139217","DOI":"10.1016\/j.jclepro.2023.139217","article-title":"Deep learning\nwith data preprocessing methods for water quality prediction in ultrafiltration\n[J]","volume":"428","author":"SHIM","year":"2023","journal-title":"Journal of Cleaner Production"},{"issue":"2","key":"2026091511122130200_cit113","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal\nMachine\nLearning: A Survey and Taxonomy [J]","volume":"41","author":"BALTRUS\u030cAITIS","year":"2019","journal-title":"IEEE Transactions\non Pattern Analysis and Machine Intelligence"},{"key":"2026091511122130200_cit114","doi-asserted-by":"publisher","first-page":"149806","DOI":"10.1016\/j.cej.2024.149806","article-title":"Physics-informed\ndeep learning for\nmulti-species membrane separations [J]","volume":"485","author":"REHMAN","year":"2024","journal-title":"Chemical\nEngineering Journal"},{"issue":"6","key":"2026091511122130200_cit115","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed\nmachine learning [J]","volume":"3","author":"KARNIADAKIS","year":"2021","journal-title":"Nature Reviews Physics"},{"issue":"1","key":"2026091511122130200_cit116","doi-asserted-by":"publisher","first-page":"10918","DOI":"10.1038\/s41467-024-55320-9","article-title":"Elucidating\ngoverning factors of PFAS removal by polyamide membranes using machine\nlearning and molecular simulations [J]","volume":"15","author":"JEONG","year":"2024","journal-title":"Nat.\nCommun."},{"key":"2026091511122130200_cit117","doi-asserted-by":"publisher","first-page":"118208","DOI":"10.1016\/j.memsci.2020.118208","article-title":"Multi-scale\nmembrane process optimization with high-fidelity ion transport models\nthrough machine learning [J]","volume":"608","author":"RALL","year":"2020","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit118","doi-asserted-by":"publisher","first-page":"132012","DOI":"10.1016\/j.seppur.2025.132012","article-title":"Fast solution\nof 3D transport processes\nusing a physics-informed neural network with embedded transfer learning\n[J]","volume":"363","author":"LIU","year":"2025","journal-title":"Sep. Purif. Technol."},{"key":"2026091511122130200_cit119","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.carbon.2018.11.048","article-title":"Molecular\ninsights into multilayer 18-crown-6-like graphene nanopores for K+\/Na+\nseparation: A molecular dynamics study [J]","volume":"144","author":"CHEN","year":"2019","journal-title":"Carbon"},{"key":"2026091511122130200_cit120","doi-asserted-by":"publisher","first-page":"123577","DOI":"10.1016\/j.memsci.2024.123577","article-title":"Molecular dynamics analysis\nof Li+\/Mg2+ transport mechanism in COF membranes with flexible oxygen-containing\nside chains [J]","volume":"717","author":"LI","year":"2025","journal-title":"J. Membr. Sci."},{"key":"2026091511122130200_cit121","doi-asserted-by":"publisher","first-page":"123438","DOI":"10.1016\/j.watres.2025.123438","article-title":"DFT-assisted machine\nlearning for polyester membrane design in textile wastewater recovery\napplications [J]","volume":"279","author":"LIU","year":"2025","journal-title":"Water Res."},{"issue":"1","key":"2026091511122130200_cit122","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1038\/s41524-025-01681-8","article-title":"Polymer\ndesign for solvent separations by integrating simulations, experiments\nand known physics via machine learning [J]","volume":"11","author":"NISTANE","year":"2025","journal-title":"npj Computational Materials"},{"issue":"27","key":"2026091511122130200_cit123","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adf8412","article-title":"Dehydration-enhanced\nion-pore interactions dominate anion transport and selectivity in\nnanochannels [J]","volume":"9","author":"LU","year":"2023","journal-title":"Science Advances"},{"key":"2026091511122130200_cit124","doi-asserted-by":"publisher","first-page":"136364","DOI":"10.1016\/j.chemosphere.2022.136364","article-title":"Deep reinforcement\nlearning in an ultrafiltration system: Optimizing operating pressure\nand chemical cleaning conditions [J]","volume":"308","author":"PARK","year":"2022","journal-title":"Chemosphere"},{"issue":"4","key":"2026091511122130200_cit125","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1021\/acs.est.1c04373","article-title":"Revolutionizing Membrane\nDesign Using Machine Learning-Bayesian Optimization [J]","volume":"56","author":"GAO","year":"2022","journal-title":"Environ. Sci. Technol."},{"issue":"8","key":"2026091511122130200_cit126","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/s44221-024-00279-6","article-title":"Designing membranes with specific binding sites for selective ion\nseparations [J]","volume":"2","author":"VIOLET","year":"2024","journal-title":"Nature Water"},{"key":"2026091511122130200_cit127","doi-asserted-by":"publisher","first-page":"118809","DOI":"10.1016\/j.memsci.2020.118809","article-title":"Pore model for nanofiltration:\nHistory,\ntheoretical framework, key predictions, limitations, and prospects\n[J]","volume":"620","author":"WANG","year":"2021","journal-title":"J. Membr. Sci."},{"issue":"1","key":"2026091511122130200_cit128","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.desal.2005.12.033","article-title":"Removal\nof endocrine disrupting compounds and pharmaceuticals by nanofiltration\nand ultrafiltration membranes [J]","volume":"202","author":"YOON","year":"2007","journal-title":"Desalination"},{"key":"2026091511122130200_cit129","doi-asserted-by":"publisher","first-page":"122161","DOI":"10.1016\/j.seppur.2022.122161","article-title":"Evaluating the efficiency\nof nanofiltration and reverse osmosis membrane processes for the removal\nof per- and polyfluoroalkyl substances from water: A critical review\n[J]","volume":"302","author":"LIU","year":"2022","journal-title":"Sep. Purif. Technol."},{"key":"2026091511122130200_cit130","doi-asserted-by":"publisher","first-page":"117672","DOI":"10.1016\/j.memsci.2019.117672","article-title":"Removal\nof organic micropollutants using advanced membrane-based water and\nwastewater treatment: A review [J]","volume":"598","author":"KHANZADA","year":"2020","journal-title":"J. Membr.\nSci."},{"key":"2026091511122130200_cit131","doi-asserted-by":"publisher","first-page":"119130","DOI":"10.1016\/j.watres.2022.119130","article-title":"Modeling micropollutant removal by nanofiltration\nand reverse osmosis membranes: considerations and challenges [J]","volume":"225","author":"Castano Osorio","year":"2022","journal-title":"Water Res."},{"issue":"2","key":"2026091511122130200_cit132","doi-asserted-by":"publisher","first-page":"243","DOI":"10.5802\/crchim.76","article-title":"An artificial\nintelligence\napproach for modeling the rejection of anti-inflammatory drugs by\nnanofiltration and reverse osmosis membranes using kernel support\nvector machine and neural networks [J]","volume":"24","author":"AMMI","year":"2021","journal-title":"Comptes\nRendus Chimie"},{"issue":"6","key":"2026091511122130200_cit133","doi-asserted-by":"publisher","first-page":"2008","DOI":"10.1021\/es062052f","article-title":"Effect\nof Flux (Transmembrane Pressure) and Membrane Properties on Fouling\nand Rejection of Reverse Osmosis and Nanofiltration Membranes Treating\nPerfluorooctane Sulfonate Containing Wastewater [J]","volume":"41","author":"TANG","year":"2007","journal-title":"Environ. Sci. Technol."},{"issue":"14","key":"2026091511122130200_cit134","doi-asserted-by":"publisher","first-page":"5292","DOI":"10.1021\/es703207s","article-title":"Nanofiltration for\nTrace Organic\nContaminant Removal: Structure, Solution, and Membrane Fouling Effects\non the Rejection of Perfluorochemicals [J]","volume":"42","author":"STEINLE-DARLING","year":"2008","journal-title":"Environ. Sci. Technol."},{"issue":"14","key":"2026091511122130200_cit135","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1016\/j.watres.2008.05.020","article-title":"Rejection\nof pharmaceuticals in nanofiltration and reverse osmosis membrane\ndrinking water treatment [J]","volume":"42","author":"RADJENOVIC\u0301","year":"2008","journal-title":"Water Res."},{"issue":"4","key":"2026091511122130200_cit136","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1039\/D4DD00395K","article-title":"Benchmarking study of\ndeep generative models for inverse polymer design [J]","volume":"4","author":"YUE","year":"2025","journal-title":"Digital Discovery"},{"key":"2026091511122130200_cit137","doi-asserted-by":"publisher","first-page":"101238","DOI":"10.1016\/j.dwt.2025.101238","article-title":"Harnessing\nmachine learning for transmembrane pressure prediction in MBR systems\nduring textile wastewater treatment [J]","volume":"322","author":"ZAHOOR","year":"2025","journal-title":"Desalination\nand Water Treatment"},{"issue":"9","key":"2026091511122130200_cit138","first-page":"78","article-title":"Construction\nof machine learning model driven by attention mechanism for AnMBR\nmembrane fouling prediction","volume":"45","author":"Xie","year":"2025","journal-title":"Industrial Water\nTreatment"},{"issue":"6","key":"2026091511122130200_cit139","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s11783-026-2186-9","article-title":"Machine learning for\nsmall-data in aquatic environments: a review of challenges, methods,\nand optimization approaches [J]","volume":"20","author":"CHEN","year":"2026","journal-title":"ENGINEERING\nEnvironment"},{"issue":"1","key":"2026091511122130200_cit140","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11783-026-2103-2","article-title":"Automated\nmachine learning-based reverse osmosis membrane flux prediction and\nchemical dosage dynamic adjustment [J]","volume":"20","author":"CHENG","year":"2026","journal-title":"ENGINEERING\nEnvironment"}],"container-title":["Environmental Science &amp;\nTechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.est.6c07517","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/esthag\/article-pdf\/60\/36\/25088\/67577185\/acs.est.6c07517.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/esthag\/article-pdf\/60\/36\/25088\/67577185\/acs.est.6c07517.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T15:53:44Z","timestamp":1789487624000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/esthag\/article\/60\/36\/25088\/5346648\/Data-Mechanism-Fusion-for-Deep-Learning-Enabled"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":140,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2026,8,28]]},"published-print":{"date-parts":[[2026,9,15]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.est.6c07517","relation":{},"ISSN":["0013-936X","1520-5851"],"issn-type":[{"value":"0013-936X","type":"print"},{"value":"1520-5851","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}