Machine-Learning Potentials for Simulating CO₂ Chemisorption

Abstract

The application of solid sorbent materials for carbon capture has been proposed as an alternative to amine-based liquid sorbents due to their lower desorption energy requirement. Among various types of porous solid sorbent, metal-organic frameworks (MOFs) are highly promising because they typically exhibit both high $$CO_2$$ uptake and $$CO_2/N_2$$ selectivity, which are required for carbon capture. The chemisorption of $$CO_2$$ in MOFs (such as on open metal sites) generally yields an extremely high $$CO_2/N_2$$ selectivity, manifesting itself more prominently at lower partial pressures (which is particularly relevant for direct air capture). The atomistic modelling of this process (e.g. bond forming) cannot be performed using efficient classical force fields and requires the first-principle based simulation. The latter is still computationally costly and is not suitable for screening a large amount of MOFs. Here, we report the quantum-informed machine-learning potentials for atomistic simulations, including both molecular dynamics (MD) and grand canonical monte carlo (GCMC), of $$CO_2$$ in MOFs. We demonstrate that the method has a much higher computational efficiency than the first-principle one while predicting accurate forces on atoms (in MD simulations) and energies (in GCMC simulations). We further explored the transferability of machine-learning potentials among MOFs with similar atomic structures.