Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems

TL;DR

This paper introduces a hybrid classical/machine-learning force field model that leverages high-quality ab initio data for accurate and transferable molecular simulations in condensed-phase systems, combining robustness and flexibility.

Contribution

The authors develop a hybrid ML/classical force field trained on ab initio data that is transferable to condensed-phase systems, enhancing accuracy and applicability.

Findings

Effective in modeling organic liquids and small-molecule crystals

Outperforms purely classical force fields in accuracy

Maintains computational efficiency

Abstract

Electronic structure methods offer in principle accurate predictions of molecular properties, however, their applicability is limited by computational costs. Empirical methods are cheaper, but come with inherent approximations and are dependent on the quality and quantity of training data. The rise of machine learning (ML) force fields (FFs) exacerbates limitations related to training data even further, especially for condensed-phase systems for which the generation of large and high-quality training datasets is difficult. Here, we propose a hybrid ML/classical FF model that is parametrized exclusively on high-quality ab initio data of dimers and monomers in vacuum but is transferable to condensed-phase systems. The proposed hybrid model combines our previous ML-parametrized classical model with ML corrections for situations where classical approximations break down, thus combining the robustness and efficiency of classical FFs with the flexibility of ML. Extensive validation on benchmarking datasets and experimental condensed-phase data, including organic liquids and small-molecule crystal structures, showcases how the proposed approach may promote FF development and unlock the full potential of classical FFs.