随着人工智能技术的飞速发展,机器学习作为人工智能的核心分支,已经在多个领域大放异彩。膜材料领域作为现代化学工程的基石,其性能优化和设计创新一直是研究的热点。机器学习算法能够快速筛选和评估膜材料的候选结构并预测其在不同条件下的性能表现,加快膜材料的研发进度。首先介绍了机器学习算法流程及常见的机器学习模型,然后总结归纳目前已有的膜材料公开数据集,接着总结了机器学习在膜设计与制造、膜性能预测、辅助膜筛选和优化等领域的研究成果,最后讨论了机器学习在膜材料研发中面临的挑战并展望其发展前景。
With the rapid development of artificial intelligence technology,machine learning,as a core branch of artificial intelligence,has made a splash in many fields.The field of membrane materials,as the cornerstone of modern chemical engineering,has been a hot research topic for its performance optimization and design innovation.Machine learning algorithms can quickly screen and evaluate the candidate structures of membrane materials and predict their performance under different conditions,accelerating the development of membrane materials.This paper firstly introduced the machine learning algorithm workflow and common machine learning models,then summarized the existing public datasets of membrane materials.Following that,it reviewed the research achievements of machine learning in the fields of membrane design and fabrication,membrane performance prediction,and assisted membrane screening and optimization.Finally,it discussed the challenges faced by machine learning in the research and development of membrane materials,and looked forward to the prospect of its development.
[1] Wei J,Chu X,Sun X Y,et al.Machine learning in materials science[J].Information Material,2019,1(3):338-358.
[2] Sutrisna P D,Kurnia K A,Siagian U W R,et al.Membrane fouling and fouling mitigation in oil-water separation:A review[J].Journal of Environmental Chemical Engineering,2022,10(3):107532.
[3] Terlouw T,Bauer C,Mckenna R,et al.Large-scale hydrogen production via water electrolysis:a techno-economic and environmental assessment[J].Energy & Environmental Science,2022,15(9):3583-3602.
[4] Barhoum A,Pal K,Rahier H,et al.Nanofibers as new-generation materials:from spinning and nano-spinning fabrication techniques to emerging applications[J].Applied Materials Today,2019,17:1-35.
[5] Yin H Y,Xu M Z,Luo Z Y,et al.Machine learning for membrane design and discovery[J].Green Energy & Environment,2024,9(1):54-70.
[6] 车万翔,窦志成,冯岩松,等.大模型时代的自然语言处理:挑战、机遇与发展[J].中国科学:信息科学,2023,53(9):1645-1687.
[7] Citko W,Sienko W.Inpainted image reconstruction using an extended Hopfield neural network-based machine learning system[J].Sensors,2022,22(3):813.
[8] Wang B,Wang X K,Wang N,et al.Machine learning optimization model for reducing the electricity loads in residential energy forecasting[J].Sustainable Computing-Informatics & Systems,2023,38:100876.
[9] Kumar A,Chauhan T,Natesan S,et al.Towards an efficient machine learning model for financial time series forecasting[J].Soft Computing,2023,27(16):11329-11339.
[10] Cao Z L,Barati F O,Ock J,et al.Machine learning in membrane design:From property prediction to ai-guided optimization[J].Nano Letters,2024,24(10):2953-2960.
[11] Cao Y H,Wang X J,Wang Y H,et al.Analysis of factors affecting the severity of marine accidents using a data-driven bayesian network[J].Ocean Engineering,2023,269:113563.
[12] Austin P C,Steyerberg E W.The number of subjects per variable required in linear regression analyses[J].Journal of Clinical Epidemiology,2015,68(6):627-636.
[13] Sperandei S.Understanding logistic regression analysis[J].Biochemia Medica,2014,24(1):12-18.
[14] Dong S,Wang P,Abbas K.A survey on deep learning and its applications[J].Computer Science Review,2021,40:100379.
[15] Chauhan V K,Dahiya K,Sharma A.Problem formulations and solvers in linear svm:a review[J].Artificial Intelligence Review,2019,52(2):803-855.
[16] Kaminski B,Jakubczyk M,Szufel P.A framework for sensitivity analysis of decision trees[J].Central European Journal of Operations Research,2018,26(1):135-159.
[17] Chen Y Y,Zheng W Z,Li W B,et al.Large group activity security risk assessment and risk early warning based on random forest algorithm[J].Pattern Recognition Letters,2021,144:1-5.
[18] Shafiq A,Colak A B,Lone S A,et al.Reliability modeling and analysis of mixture of exponential distributions using artificial neural network[J].Mathematical Methods in the Applied Sciences,2024,47(5):3308-3328.
[19] Chung Y G,Camp J,Haranczyk M,et al.Computation-ready,experimental metal-organic frameworks:a tool to enable high-throughput screening of nanoporous crystals[J].Chemistry of Materials,2014,26(21):6185-6192.
[20] Tong M M,Lan Y S,Yang Q Y,et al.Exploring the structure-property relationships of covalent organic frameworks for noble gas separations[J].Chemical Engineering Science,2017,168:456-464.
[21] Wilmer C E,Leaf M,Lee C Y,et al.Large-scale screening of hypothetical metal-organic frameworks[J].Nature Chemistry,2012,4(2):83-89.
[22] Malde A K,Zuo L,Breeze M,et al.An automated force field topology builder (atb) and repository:Version 1.0[J].Journal of Chemical Theory and Computation,2011,7(12):4026-4037.
[23] Xu Y B,Yamazaki M,Villars P.Inorganic materials database for exploring the nature of material[J].Japanese Journal of Applied Physics,2011,50(11):11RH02.
[24] Groom C R,Bruno I J,Lightfoot M P,et al.The cambridge structural database[J].Acta Crystallographica Section B-Structural Science Crystal Engineering and Materials,2016,72:171-179.
[25] Winther K,Hoffmann M,Mamun O,et al.Catalysis-hub.org:an open electronic structure database for surface reactions and catalytic materials[J].Abstracts of Papers of the American Chemical Society,2019,257:88.
[26] Irikura K K,Johnson R D,Kacker R N Uncertainties in scaling factors for ab initio vibrational frequencies[J].Journal of Physical Chemistry A,2005,109(37):8430-8437.
[27] Haastrup S,Strange M,Pandey M,et al.The computational 2D materials database:High-throughput modeling and discovery of atomically thin crystals[J].2D Materials,2018,5(4):042002.
[28] Zagorac D,Mueller H,Ruehl S,et al.Recent developments in the inorganic crystal structure database:theoretical crystal structure data and related features[J].Journal of Applied Crystallography,2019,52:918-925.
[29] Borysov S S,Geilhufe R M,Balatsky A V.Organic materials database:an open-access online database for data mining[J].Plos One,2017,12(2):e0171501.
[30] Kim C,Chandrasekaran A,Tran D H,et al.Polymer genome:a data-powered polymer informatics platform for property predictions[J].Journal of Physical Chemistry C,2018,122(31):17575-17585.
[31] Kirklin S,Saal J E.,Meredig B,et al.The open quantum materials database (oqmd):Assessing the accuracy of dft formation energies[J].npj Computational Materials,2015,1:15010.
[32] Barnett J W,Bilchak C R,Wang Y W,et al.Designing exceptional gas-separation polymer membranes using machine learning[J].Science Advances,2020,6(20):eaaz4301.
[33] Yang J S,Tao L,He J L,et al.Machine learning enables interpretable discovery of innovative polymers for gas separation membranes[J].Science Advances,2022,8(29):eabn9545.
[34] Namsheer K,Rout C S.Conducting polymers:a comprehensive review on recent advances in synthesis,properties and applications[J].RSC Advances,2021,11(10):5659-5697.
[35] Guan J,Huang T,Liu W,et al.Design and prediction of metal organic framework-based mixed matrix membranes for Co2 capture via machine learning[J].Cell Reports Physical Science,2022,3(5):100864.
[36] Gao H P,Zhong S F,Zhang W L,et al.Revolutionizing membrane design using machine learning-bayesian optimization[J].Environmental Science & Technology,2021,56(4):2572-2581.
[37] Hancock J T,Khoshgoftaar T M.Catboost for big data:an interdisciplinary review[J].Journal of Big Data,2020,7(1):94.
[38] Wang C,Wang L,Soo A,et al.Machine learning based prediction and optimization of thin film nanocomposite membranes for organic solvent nanofiltration[J].Separation and Purification Technology,2023,304:122328.
[39] Johnson D J,Hilal N.Can graphene and graphene oxide materials revolutionise desalination processes？[J].Desalination,2021,500:114852.
[40] Sheshanarayana R,Rajan A Govind.Tailoring nanoporous graphene via machine learning:Predicting probabilities and formation times of arbitrary nanopore shapes[J].Journal of Chemical Physics,2022,156(20):204703.
[41] Xu Q S,Jiang J W.Recent development in machine learning of polymer membranes for liquid separation[J].Molecular Systems Design & Engineering,2022,7(8):856-872.
[42] Zhang Z Y,Luo Y T,Peng H W,et al.Deep spatial representation learning of polyamide nanofiltration membranes[J].Journal of Membrane Science,2021,620:118910.
[43] Fetanat M,Keshtiara M,Low Z X,et al.Machine learning for advanced design of nanocomposite ultrafiltration membranes[J].Industrial & Engineering Chemistry Research,2021,60(14):5236-5250.
[44] Bagheri M,Akbari A,Mirbagheri S A.Advanced control of membrane fouling in filtration systems using artificial intelligence and machine learning techniques:A critical review[J].Process Safety and Environmental Protection,2019,123:229-252.
[45] Liang H,Jiang K,Yan T A,et al.Xgboost:an optimal machine learning model with just structural features to discover mof adsorbents of Xe/Kr[J].ACS Omega,2021,6(13):9066-9076.
[46] 程敏,王诗慧,罗磊,等.面向乙烷/乙烯分离的金属有机框架膜的大规模计算筛选[J].化学学报,2022,80(9):1277-1288.
[47] Deshwal A,Simon C M,Doppa J R.Bayesian optimization of nanoporous materials[J].Molecular Systems Design & Engineering,2021,6(12):1066-1086.
[48] 王璐,张磊,都健.机器学习高效筛选用于CO2/N2选择性吸附分离的沸石材料[J].化工进展,2023,42(1):148-158.
[49] Wang M,Xu Q S,Tang H J,et al.Machine learning-enabled prediction and high-throughput screening of polymer membranes for pervaporation separation[J].ACS Applied Materials & Interfaces,2022,14(6):8427-8436.
基金资助
国家重点研发计划(2022YFB3805201)
PDF
