Prediction of CO2 Adsorption in Nano-Pores with Graph Neural Networks

We investigate the graph-based convolutional neural network approach for predicting and ranking the gas adsorption properties of crystalline Metal-Organic Framework (MOF) adsorbents for application in post-combustion capture of carbon dioxide. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of classical machine learning models which were built with hundreds of features at much higher computational cost. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.