High-Throughput Computational Screening and Machine Learning Model for Accelerated Metal-Organic Frameworks Discovery in Toluene Vapor Adsorption

Some hazardous gases, like toluene vapor, have causedserious environmentalpollution. The adsorption of toluene using metal-organic frameworks(MOFs) has been considered a useful mechanism to reduce environmentalpollution. High-throughput computation using the grand canonical MonteCarlo (GCMC) approach was used to screen high-performance MOFs fromthe CoRE MOF database. A total of 802 MOFs are selected with a tolueneuptake larger than HKUST-1 (6.34 mmol/g at 1900 Pa, 298 K) and CMOF-3b([(L3b)Cu-2]( n ), L3b = 4,4 ',4 '',4"'-(2,2 '-dihydroxy-1,1 '-binaphthalene-4,4 ',6,6 '-tetrayl)),showing the highest toluene vapor adsorption capacity (25.57 mmol/g).Approximately 80% of high-performance MOFs contain open metal sites.Further analyses of the quantitative structure-property relationshipsreveal that the MOF adsorption capacity for toluene could be primarilycorrelated with gravimetric surface area and void fraction. Moreover,using the HKUST-1 as a template, center-metal element replacementis suggested to be effective in improving toluene vapor adsorption.Finally, based on our previously proposed MOF-CGCNN algorithm, a regressionmodel is developed to predict toluene adsorption capacity. Combinedwith high-throughput GCMC calculation, the machine learning modelis applied to screen a larger MOF database (containing 137,953 hypotheticalMOFs), which accelerates the virtual discovery of new high-performancecandidate MOFs for toluene adsorption. The proposed strategy willbe useful in material design or discovery for reducing toluene, therebybenefitting the environment.