Prediction by Convolutional Neural Networks of CO2 /N2 Selectivity in Porous Carbons from N2 Adsorption Isotherm at 77 K.

Porous carbons are an important class of porous materials with many applications, including gas separation. An N2 adsorption isotherm at 77 K is the most widely used approach to characterize porosity. Conventionally, textual properties such as surface area and pore volumes are derived from the N2 adsorption isotherm at 77 K by fitting it to adsorption theory and then correlating it to gas separation performance (uptake and selectivity). Here the N2 isotherm at 77 K was used directly as input (representing feature descriptors for the porosity) to train convolutional neural networks to predict gas separation performance (using CO2 /N2 as a test case) for porous carbons. The porosity space for porous carbons was explored for higher CO2 /N2 selectivity. Porous carbons with a bimodal pore-size distribution of well-separated mesopores (3-7 nm) and micropores (<2 nm) were found to be most promising. This work will be useful in guiding experimental research of porous carbons with the desired porosity for gas separation and other applications.