Enhancing Gas Separation Selectivity Prediction through Novel Descriptors

Adsorption-based techniques for gas separation using nanoporous materials are widely used and hold a promising future, but systematic identification of the best-performing materials for a given application is still an open problem. For that task, we need to estimate selectivity at different operating conditions (temperature, pressure) on a large set of nanoporous structures. To this aim, we have developed a machine learning-assisted screening process based on a fast grid calculation of interaction energies, in addition to newly designed geometrical descriptors to predict ambient-pressure selectivity. As a proof of concept, we tested our methodology for the separation of a 20-80 xenon/krypton mixture at 298 K and 1 atm in the nanoporous materials of the CoRE MOF 2019 database. Based on a standard train/test split of the dataset, our model is promising with an RMSE of 2.5 on the ambient-pressure selectivity values of the test set and 0.06 on the log10 of the selectivity. This method can thence be used to pre-select the best performing materials for a more thorough investigation.