Quantitative Structure–Property Relationship Models for Recognizing Metal Organic Frameworks (MOFs) with High CO2 Working Capacity and CO2/CH4 Selectivity for Methane Purification. Issue 27 (15th June 2016)

• Record Type: Journal Article
• Authors: Aghaji, Mohammad Zein; Fernandez, Michael; Boyd, Peter G.; Daff, Thomas D.; Woo, Tom K.
• Other Names: Dietzel Pascal D. C. guestEditor.; Kitagawa Hiroshi guestEditor.
• Is Part Of: European journal of inorganic chemistry. Issue 27(2016)
• Page Start: 4505
• Page End: 4511
• Publication Date: 2016-06-15
• Subjects: Metal organic frameworks -- Nanoporous solids -- Adsorption -- Gas separation -- Screening -- Carbon dioxide -- Methane; Chemistry, Inorganic -- Periodicals; Organometallic chemistry -- Periodicals; Bioinorganic chemistry -- Periodicals; Solid state chemistry -- Periodicals; 546
• DOI: 10.1002/ejic.201600365
• Languages: English
• ISSNs: 1434-1948

Abstract

Abstract : 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 CO2 working capacity and CO2 /CH4 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. Abstract : Robust machine learning QSPR models have been developed to accurately recognize high‐performing metal organic framework materials for both the working capacity and selectivity in CO2 /CH4 gas separations under methane purification conditions. The models were trained on 32, 500 MOFs and validated on a test set of ca. 290, 000 hypothetical MOFs.