Machine learning using host/guest energy histograms to predict adsorption in metal-organic frameworks: Application to short alkanes and Xe/Kr mixtures
Machine learning using host/guest energy histograms to predict adsorption in metal-organic frameworks: Application to short alkanes and Xe/Kr mixtures
复制标题
DOI：
10.1063/5.0050823
复制
发表时间：
2021-07-07
影响因子：
4.4
通讯作者：
Snurr, Randall Q.
中科院分区：
文献类型：
--
作者：
Li, Zhao;Bucior, Benjamin J.;Snurr, Randall Q.
使用相互作用能直方图的机器学习（ML）方法已被应用于预测金属有机框架（MOF）中的气体吸附，使用来自原子巨正则蒙特卡罗（GCMC）模拟的结果作为训练和测试数据。在这项工作中，该方法首先扩展到二元混合物的球形物种，特别是，氘和氪。此外，它表明，乙烷和丙烷的单组分吸附可以预测与GCMC模拟使用直方图的甲基探针与随机森林ML方法相结合的吸附能感觉到很好的一致性。丙烷的结果可以通过包括少量的MOF纹理特性作为描述符来改进。我们还讨论了最重要的功能，它提供了物理洞察到最有益的吸附能量网站为给定的应用程序。
A machine learning (ML) methodology that uses a histogram of interaction energies has been applied to predict gas adsorption in metal-organic frameworks (MOFs) using results from atomistic grand canonical Monte Carlo (GCMC) simulations as training and test data. In this work, the method is first extended to binary mixtures of spherical species, in particular, Xe and Kr. In addition, it is shown that single-component adsorption of ethane and propane can be predicted in good agreement with GCMC simulation using a histogram of the adsorption energies felt by a methyl probe in conjunction with the random forest ML method. The results for propane can be improved by including a small number of MOF textural properties as descriptors. We also discuss the most significant features, which provides physical insight into the most beneficial adsorption energy sites for a given application.