### 基于机器学习和高通量计算筛选金属有机框架的甲烷/乙烷/丙烷分离性能

1. 广州大学化学化工学院 能源与催化研究所 广州 510006
• 投稿日期:2020-03-13 发布日期:2020-04-16
• 通讯作者: 乔智威 E-mail:zqiao@gzhu.edu.cn
• 基金资助:
项目受国家自然科学基金（Nos.21978058，21676094，21576058）和广东省自然科学基金（No.2020A1515010800）资助.

### Machine Learning and High-throughput Computational Screening of Metal-organic Framework for Separation of Methane/ethane/propane

Cai Chengzhi, Li Lifeng, Deng Xiaomei, Li Shuhua, Liang Hong, Qiao Zhiwei

1. Guangzhou Key Laboratory for New Energy and Green Catalysis, School of Chemistry and Chemical Engineering, Guangzhou University, Guangzhou 510006
• Received:2020-03-13 Published:2020-04-16
• Supported by:
Project supported by the National Natural Science Foundation of China (Nos. 21978058, 21676094, 21576058) and the Natural Science Foundation of Guangdong Province (No. 2020A1515010800).

In this work, the separation performance of methane/ethane/propane (C1, C2 and C3) mixture in the 137953 hypothetical metal-organic frameworks (MOFs) is calculated by high throughput computational screening and multiple machine learning (ML) algorithms. First, to avoid the competitive adsorption of water vapor, 31399 hydrophobic MOFs (hMOFs) were screened out. Then, grand canonical Monte Carlo (GCMC) simulations were employed to calculate the adsorption behavior of a mixture with a mole ratio of C1:C2:C3=7:2:1 in these hMOFs, respectively. Second, the relationships among six MOF structures/energy descriptors (the largest cavity diameter (LCD), void fraction (f), volumetric surface area (VSA), Henry coefficient (K), heat of adsorption (Qst), density of MOF (ρ)) and three performance indicators of MOFs (selectivities (S), adsorption capacities (N) of C1, C2, C3 and their trade-offs (TSN)) were established. The LCDs were calculated by Zeo++software, and VSAs were calculated using RASPA software using He and N2 as probes, respectively, and Qst and K were calculated in an infinite dilution of each gas molecule in an infinite dilution state using NVT-MC method in RASPA software. Then, we found that there existed the "second peaks" of N and S in part of structure-property relationships, and all the optimal MOFs located in the range of second peaks, especially for the separation of C1 or C2. Third, the above-mentioned six MOF descriptors and three MOF performance indicators were trained, tested and predicted by four ML algorithms, including decision tree, random forest (RF), support vector machine and Back Propagation neural network. Although the predictive effect for the selectivity was very low, the introduction of TSN can significantly improve the accuracy of ML prediction, especially for RF algorithm (R=0.99). Therefore, the RF was used to quantitatively analyze the relative importance of each MOF descriptor, and found that three descriptors (K, LCD and ρ) possessed the highest importance for the separation of C1 and C2, and three other descriptors (K, Qst and ρ) for the separation of C3. Moreover, three simple and clear paths of optimal MOFs for C1, C2 and C3 adsorption were designed by the decision tree model with the descriptors. Based on those paths, there were 96%, 85%, 95% probability that we can search for high-performance MOFs, respectively. Finally, the best 18 MOFs were identified for different separation applications of C1, C2 and C3. This study reveals the second peaks and key MOF descriptors governing the adsorption of light alkane, develops quantitative structure-property relationships by ML, and identifies the best adsorbents from a large collection of MOFs for the separation of C1, C2 and C3 from natural gas.