QM/MM Methods for Crystalline Defects. Part 3: Machine-Learned Interatomic Potentials

TL;DR

This paper introduces a framework for hybrid quantum/classical models of crystalline defects that incorporates machine-learned interatomic potentials, providing error estimates and practical construction methods for improved simulations.

Contribution

It develops a unified approach to integrate machine-learned interatomic potentials into QM/MM models with error analysis and construction techniques.

Findings

Established an a priori error estimate for QM/MM approximations.

Demonstrated construction of machine-learned MM potentials for QM/MM simulations.

Unified framework accommodating traditional and machine-learned potentials.

Abstract

We develop and analyze a framework for consistent QM/MM (quantum/classic) hybrid models of crystalline defects, which admits general atomistic interactions including traditional off-the-shell interatomic potentials as well as state of art "machine-learned interatomic potentials". We (i) establish an a priori error estimate for the QM/MM approximations in terms of matching conditions between the MM and QM models, and (ii) demonstrate how to use these matching conditions to construct practical machine learned MM potentials specifically for QM/MM simulations.