Premium
Quantitative Structure–Property Relationship Models for Recognizing Metal Organic Frameworks (MOFs) with High CO 2 Working Capacity and CO 2 /CH 4 Selectivity for Methane Purification
Author(s) -
Aghaji Mohammad Zein,
Fernandez Michael,
Boyd Peter G.,
Daff Thomas D.,
Woo Tom K.
Publication year - 2016
Publication title -
european journal of inorganic chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.667
H-Index - 136
eISSN - 1099-0682
pISSN - 1434-1948
DOI - 10.1002/ejic.201600365
Subject(s) - support vector machine , metal organic framework , chemistry , nanoporous , quantitative structure–activity relationship , cosmo rs , methane , virtual screening , fraction (chemistry) , porosity , rational design , adsorption , artificial intelligence , computer science , nanotechnology , computational chemistry , organic chemistry , materials science , molecular dynamics , ionic liquid , stereochemistry , catalysis
Metal‐organic frameworks (MOFs) can theoretically yield a nearly infinite number of nanoporous materials, which represents a combinatorial design challenge that demands computational tools rather than experimental trial‐and‐error. Here we report Quantitative Structure–Property Relationship (QSPR) models to identify high‐performing MOFs for methane purification solely using geometrical features. The CO 2 working capacity and CO 2 /CH 4 selectivity of ca. 320,000 hypothetical MOF structures was computed at conditions relevant to natural gas purification using grand canonical Monte‐Carlo (GCMC) simulations. Using 32,500 MOF structures we calibrated binary decision tree (DT) and support vector machine (SVM) models that can accurately identify high‐performing MOFs based on their pore size, void fraction and surface area. DT models yielded guidelines of pore size, void fraction and surface area for designing high‐performing materials. The SVM machine learning classifiers could be used to quickly pre‐screen MOFs, such that compute intensive GCMC simulations are not performed on all structures. The SVM classifiers were tested on ca. 290,000 MOFs that were not part of the training set and could correctly identify up to 90 % of high‐performing MOFs while only flagging a fraction of the MOFs for more rigorous screening. QSPR models constitute efficient computational tools for the virtual screening of large structural libraries and provide rational design rules for the discovery of sorbents for methane purification.