Prediction of solvent aggregation in CO2-loaded aqueous amines using machine learning molecular dynamics simulations

Aggregation of ion pairs formed during CO2 capture may govern absorption thermodynamics and kinetics, but it is often overestimated by fixed-charge classical force fields. Here, we demonstrate the promise of graph neural network interatomic potentials, which offer quantum-level accuracy, for directly evaluating the aggregation tendencies of ionic products in CO2-loaded aqueous amine solutions.