Prediction of the Diffusion Coefficient through Machine Learning Based on Transition-State Theory Descriptors

Abstract

Nanoporous materials serve as very effective media for storing and separating small molecules. To design the best materials for a given application based on adsorption, one usually assesses the equilibrium performance by using key thermodynamic quantities such as Henry constants or adsorption loading values. To go beyond standard methodologies, we probe here the transport effects occurring in the material by studying the self-diffusion coefficients of xenon inside the nanopores of the framework materials. We find good correlations between the diffusion coefficients and the pore aperture size as well as other geometrical and energetic descriptors. We used extensive molecular dynamics simulations to calculate the diffusion coefficient of xenon in 4873 MOFs from the CoRE MOF 2019 database, the first large-scale database of transport properties published at this scale. Based on these data, we present a tool to quickly evaluate the diffusion energy barrier that proved to be very correlated to the diffusion rate. This descriptor, alongside other geometrical characterizations, was then used to build a machine learning model that can predict the xenon diffusion coefficients in MOFs. The final trained model is quite accurate and shows a root-mean-square error on the log 10 of the diffusion coefficient equal to 0.25.

Multiscale Modeling of Physical Properties of Nanoporous Frameworks: Predicting Mechanical, Thermal, and Adsorption Behavior

“…Another approach to compute diffusion coefficients uses Transition State Theory and kinetic Monte Carlo simulations and allows considerable decrease of the computational cost . Recently, our group computed diffusion coefficients of xenon in a large subset of the CoRE MOF structural database and showed that diffusion coefficients can be efficiently predicted using ML models with fast calculations of activation energies and other geometrical descriptors . These studies pave the way to the extension of porous materials databases with kinetic descriptors, and we think this area of research has not yet seen its full potential, and many methodological developments can be expected in the near future.…”