化工学报2025，Vol.76Issue(5)：1973-1996,24.DOI:10.11949/0438-1157.20241229
机器学习辅助MOFs高通量计算筛选及气体分离研究进展
Machine learning-assisted high-throughput computational screening of MOFs and advances in gas separation research
摘要
Abstract
Metal organic frameworks(MOFs)have garnered extensive research interest in fields such as gas storage,adsorption separation,and catalysis due to their high surface area,large pore volume,and tunable structures.In recent years,the surge in the number of MOFs has posed unprecedented challenges in finding the ideal MOF for specific applications.In this scenario,high-throughput computational screening(HTCS)has become the most effective research method for screening high-performance target MOFs from a vast array of materials.HTCS will generate a large amount of multidimensional data,which can be further used for machine learning(ML)training.Recently,applying ML to HTCS of MOFs has become a new hotspot,which can not only reveal the potential structure-performance relationships of materials but also provide insights into their performance trends in different applications,especially in gas storage and separation.In this review,we highlight the latest advances in ML-assisted HTCS in the field of MOFs gas separation,systematically analyze the internal mechanism of ML and HTCS collaboration to improve screening efficiency in the search for high-performance MOFs,and explore the opportunities and challenges presented in this new field.关键词
金属有机框架/高通量计算筛选/分子模拟/机器学习/吸附分离Key words
metal organic frameworks/high-throughput computational screening/molecular simulation/machine learning/adsorption and separation分类
化学工程引用本文复制引用
胡嘉朗,姜明源,金律铭,张永刚,胡鹏,纪红兵..机器学习辅助MOFs高通量计算筛选及气体分离研究进展[J].化工学报,2025,76(5):1973-1996,24.基金项目
国家重点研发计划项目(2020YFA0210900) （2020YFA0210900）
国家自然科学基金项目(21938001,21961160741,42177029,22308318,22408330) （21938001,21961160741,42177029,22308318,22408330）
广东省科技规划项目(STKJ2023015) （STKJ2023015）
广东省自然科学基金项目(2023B1515020101) （2023B1515020101）
广西科技项目(AA23062018) （AA23062018）
大学生创新创业训练计划项目(202410337028) （202410337028）
浙江省教育厅科研项目(Y202455550) （Y202455550）
