膜科学与技术

Position：Home >> Abstract

Research Progress of Machine Learning in MOF Gas Separation Membranes Prediction and Screening

Authors： TIAN Kai, LI Dongyang, DUAN Kun, WANG Jing, ZHANG Yatao

Units： School of Chemical Engineering, Zhengzhou University, Zhengzhou, 450001, China

KeyWords： MOF membrane; gas separation; machine learning; performance prediction and screening; molecular simulation

ClassificationCode：O604；TQ028.8

year,volume(issue):pagination： 2023,43(6):149-158

Abstract：

Metal-organic frameworks (MOFs) gas separation membranes have attracted widespread attention in the field of carbon capture and energy gas separation due to their excellent separation performance. Although the screening of high-performance MOF membranes can be achieved using high-throughput molecular simulation calculations, with the proliferation of MOFs, calculating the gas separation performance of MOF membranes one by one requires significant computational resources. Machine learning-based methods can rapidly perform the performance projection and screening of MOF membranes, thereby accelerating the design and preparation process of high-performance MOF membranes. In this paper, the methods and procedures of machine learning prediction and screening of MOF membranes are systematically presented in four aspects: data preparation, feature engineering, model training and selection, and model evaluation and interpretation. Subsequently, the current research advances in machine learning screening of pure MOF membranes and MOF hybrid matrix membranes are summarized. Finally, the challenges and future directions of machine learning screening of MOF membranes are analyzed.

Funds：

国家自然科学基金青年项目（22108258）；河南省自然科学基金优秀青年基金项目（22300420085）；河南省高校科技创新人才支持计划（24HASTIT004）

AuthorIntro：

田凯（2000-），男，湖南浏阳人，硕士研究生，研究方向为机器学习辅助设计MOF气体分离膜，E-mail：tiankai2022@126.com。

Reference：

[1] Gulbalkan H C, Haslak Z P, Altintas C, et al. Assessing CH4/N2 separation potential of MOFs, COFs, IL/MOF, MOF/Polymer, and COF/Polymer composites[J]. Chem Eng J, 2022, 428: 131239.
[2] Boyd P G, Chidambaram A, Garcia-Diez E, et al. Data-driven design of metal-organic frameworks for wet flue gas CO2 capture[J]. Nature, 2019, 576(7786): 253-256.
[3] Wei R, Liu X, Lai Z. MOF or COF membranes for olefin/paraffin separation: Current status and future research directions[J]. Adv Membr, 2022, 2: 100035.
[4] Yang L, Qian S, Wang X, et al. Energy-efficient separation alternatives: metal-organic frameworks and membranes for hydrocarbon separation[J]. Chem Soc Rev, 2020, 49(15): 5359-5406.
[5] Datta S J, Mayoral A, Murthy S B N, et al. Rational design of mixed-matrix metal-organic framework membranes for molecular separations[J]. Science, 2022, 376(6597): 1080-1087.
[6] Sholl D S, Lively R P. Seven chemical separations to change the world[J]. Nature, 2016, 532(7600): 435-437.
[7] Winarta J, Meshram A, Zhu F, et al. Metal-organic framework-based mixed-matrix membranes for gas separation: An overview[J]. J Polym Sci, 2020, 58(18): 2518-2546.
[8] Qian Q, Asinger P A, Lee M J, et al. MOF-based membranes for gas separations[J]. Chem Rev, 2020, 120(16): 8161-8266.
[9] Yaghi O M. The reticular chemist[J]. Nano Lett, 2020, 20(12): 8432-8434.
[10] Bobbitt N S, Shi K H, Bucior B J, et al. MOFX-DB: An online database of computational adsorption data for nanoporous materials[J]. J Chem Eng Data, 2023, 68(2): 483-498.
[11] Moosavi S M, Nandy A, Jablonka K M, et al. Understanding the diversity of the metal-organic framework ecosystem[J]. Nat Commun, 2020, 11(1): 4068.
[12] Colon Y J, Snurr R Q. High-throughput computational screening of metal-organic frameworks[J]. Chem Soc Rev, 2014, 43(16): 5735-49.
[13] 刘治鲁, 李炜, 刘昊, 等. 金属有机骨架的高通量计算筛选研究进展[J]. 化学学报, 2019, 77(4): 323-339.
[14] Hai G T, Wang H H. Theoretical studies of metal-organic frameworks: Calculation methods and applications in catalysis, gas separation, and energy storage[J]. Coordin Chem Rev, 2022, 469: 214670.
[15] Demir H, Daglar H, Gulbalkan H C, et al. Recent advances in computational modeling of MOFs: From molecular simulations to machine learning[J]. Coordin Chem Rev, 2023, 484: 215112.
[16] Jablonka K M, Ongari D, Moosavi S M, et al. Big-data science in porous materials: Materials genomics and machine learning[J]. Chem Rev, 2020, 120(16): 8066-8129.
[17] Chong S, Lee S, Kim B, et al. Applications of machine learning in metal-organic frameworks[J]. Coordin Chem Rev, 2020, 423: 213487.
[18] 李炜, 梁添贵, 林元创, 等. 机器学习辅助高通量筛选金属有机骨架材料[J]. 化学进展, 2022, 34(12): 2619-2637.
[19] Xu P C, Ji X B, Li M J, et al. Small data machine learning in materials science[J]. Npj Comput Mater, 2023, 9(42).
[20] Yin H, Xu M, Luo Z, et al. Machine learning for membrane design and discovery[J]. Green Energy Environ, 2022.
[21] Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine learning in python[J]. J Mach Learn Res, 2011, 12: 2825-2830.
[22] Bai X, Shi Z, Xia H, et al. Machine-learning-assisted high-throughput computational screening of metal–organic framework membranes for hydrogen separation[J]. Chem Eng J, 2022, 446: 136783.
[23] Wang J, Tian K, Li D Y, et al. Machine learning in gas separation membrane developing: Ready for prime time[J]. Sep Purif Technol, 2023, 313: 123493.
[24] Chung Y G, Haldoupis E, Bucior B J, et al. Advances, updates, and analytics for the computation-ready, experimental metal–organic framework database: CoRE MOF 2019[J]. J Chem Eng Data, 2019, 64(12): 5985-5998.
[25] Moghadam P Z, Li A, Wiggin S B, et al. Development of a cambridge structural database subset: A collection of metal–organic frameworks for past, present, and future[J]. Chem Mater, 2017, 29(7): 2618-2625.
[26] Haldoupis E, Nair S, Sholl D S. Efficient calculation of diffusion limitations in metal organic framework materials: A tool for identifying materials for kinetic separations[J]. J Am Chem Soc, 2010, 132(21): 7528-7539.
[27] Daglar H, Keskin S. Recent advances, opportunities, and challenges in high-throughput computational screening of MOFs for gas separations[J]. Coordin Chem Rev, 2020, 422: 213470.
[28] Yang Q, Liu D, Zhong C, et al. Development of computational methodologies for metal-organic frameworks and their application in gas separations[J]. Chem Rev, 2013, 113(10): 8261-323.
[29] 阳庆元, 郭翔宇, 刘大欢, 等. 纳微结构材料构效关系的计算方法研究[J]. 北京化工大学学报(自然科学版), 2015, 42(5): 1-12.
[30] 冯孝权, 刘金盾, 张亚涛. 基于MOFs的混合基质膜在C3H6/C3H8分离中的研究进展[J]. 膜科学与技术, 2020, 40(1): 204-210.
[31] Erucar I, Keskin S. Computational methods for MOF/Polymer membranes[J]. Chem Rec, 2016, 16(2): 703-18.
[32] Goh S H, Lau H S, Yong W F. Metal-organic frameworks (MOFs)-based mixed matrix membranes (MMMs) for gas separation: A review on advanced materials in harsh environmental applications[J]. Small, 2022, 18(20): e2107536.
[33] Monsalve-Bravo G M, Bhatia S K. Modeling permeation through mixed-matrix membranes: A review[J]. Processes, 2018, 6(9): 172.
[34] Daglar H, Keskin S. High-throughput screening of metal organic frameworks as fillers in mixed matrix membranes for flue gas separation[J]. Adv Theor Simul, 2019, 2(11): 1900109.
[35] Lin J, Liu Z M, Guo Y J, et al. Machine learning accelerates the investigation of targeted MOFs: Performance prediction, rational design and intelligent synthesis[J]. Nano Today, 2023, 49: 101802.
[36] Willems T F, Rycroft C H, Kazi M, et al. Algorithms and tools for high-throughput geometry-based analysis of crystalline porous materials[J]. Micropor Mesopor Mat, 2012, 149(1): 134-141.
[37] Dubbeldam D, Calero S, Ellis D E, et al. RASPA: Molecular simulation software for adsorption and diffusion in flexible nanoporous materials[J]. Mol Simul, 2015, 42(2): 81-101.
[38] Bucior B J, Rosen A S, Haranczyk M, et al. Identification schemes for metal–organic frameworks to enable rapid search and cheminformatics analysis[J]. Cryst Growth Des, 2019, 19(11): 6682-6697.
[39] 米勒. Python机器学习基础教程[M]. 北京: 人民邮电出版社, 2018: 101-105.
[40] Altintas C, Altundal O F, Keskin S, et al. Machine Learning meets with metal organic frameworks for gas storage and separation[J]. J Chem Inf Model, 2021, 61(5): 2131-2146.
[41] Wang A Y T, Murdock R J, Kauwe S K, et al. Machine learning for materials scientists: An introductory guide toward best practices[J]. Chem Mater, 2020, 32(12): 4954-4965.
[42] Wang Z H, Zhou T, Sundmacher K. Interpretable machine learning for accelerating the discovery of metal-organic frameworks for ethane/ethylene separation[J]. Chem Eng J, 2022, 444: 136651.
[43] 程敏, 王诗慧, 罗磊, 等. 乙烷/乙烯分离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.
[44] Zhou M, Vassallo A, Wu J. Toward the inverse design of MOF membranes for efficient D2/H2 separation by combination of physics-based and data-driven modeling[J]. J Membr Sci, 2020, 598: 117675.
[45] Yang W, Liang H, Peng F, et al. Computational screening of metal-organic framework membranes for the separation of 15 gas mixtures[J]. Nanomaterials (Basel), 2019, 9(3): 467.
[46] Orhan I B, Daglar H, Keskin S, et al. Prediction of O2/N2 selectivity in metal-organic frameworks via high-throughput computational screening and machine learning[J]. ACS Appl Mater Interfaces, 2022, 14(1): 736-749.
[47] Daglar H, Aydin S, Keskin S. MOF-based MMMs breaking the upper bounds of polymers for a large variety of gas separations[J]. Sep Purif Technol, 2022, 281: 119811.
[48] Daglar H, Keskin S. Combining machine learning and molecular simulations to unlock gas separation potentials of MOF membranes and MOF/Polymer MMMs[J]. ACS Appl Mater Interfaces, 2022, 14(28): 32134-32148.
[49] 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 Rep Phys Sci, 2022, 3(5): 100864.
[50] Lyu H, Ji Z, Wuttke S, et al. Digital reticular chemistry[J]. Chem, 2020, 6(9): 2219-2241.

Service：

【Download】【Collect】

《膜科学与技术》编辑部 Address: Bluestar building, 19 east beisanhuan road, chaoyang district, Beijing; 100029 Postal code; Telephone：010-80492417/010-80485372; Fax：010-80485372 ; Email：mkxyjs@163.com