Machine-learning models for atom-diatom reactions across isotopologues

Abstract

This work shows that feed-forward neural networks can predict the final rovibrational state distributions of inelastic and reactive processes of the reaction of $\mathrm{Ca}+{\mathrm{H}}_2\to \mathrm{CaH}+\mathrm{H}$ in the hyperthermal regime, relevant for buffer gas chemistry. Furthermore, these models can be extended to the isotopologues of the reaction involving deuterium and tritium. In addition, we develop a neural network model that can learn across the chemical space based on the isotopologues of hydrogen. The model can predict the outcome of a reaction whose reactants have never been seen. This is done by training on the $\mathrm{Ca}+{\mathrm{H}}_2$ and $\mathrm{Ca}+{\mathrm{T}}_2$ reactions and subsequently predicting the $\mathrm{Ca}+{\mathrm{D}}_2$ reaction.