Machine-learning based prediction of small molecule -- surface interaction potentials

TL;DR

This paper introduces a machine-learning method to accurately predict the interaction potentials and adsorption energies of small molecules on surfaces, facilitating faster and more flexible surface chemistry modeling.

Contribution

The study presents a novel machine-learning approach that predicts surface-molecule interaction potentials using separate partner potentials, trained on existing molecular dynamics data.

Findings

Good agreement between predicted and original PMFs

Model accurately predicts for molecules and surfaces outside training set

Demonstrates flexibility and predictive power of the approach

Abstract

Predicting the adsorption affinity of a small molecule to a target surface is of importance to a range of fields, from catalysis to drug delivery and human safety, but a complex task to perform computationally when taking into account the effects of the surrounding medium. We present a flexible machine-learning approach to predict potentials of mean force (PMFs) and adsorption energies for chemical -- surface pairs from the separate interaction potentials of each partner with a set of probe atoms. We use a pre-existing library of PMFs obtained via atomistic molecular dynamics for a variety of inorganic materials and molecules to train the model. We find good agreement between original and predicted PMFs in both training and validation groups, confirming the predictive power of this approach, and demonstrate the flexibility of the model by producing PMFs for molecules and surfaces outside the training set.