Upscaling DFT-trained machine-learning interatomic potential toward Quantum Monte Carlo accuracy: Sulfur-vacancy migration in monolayer MoS$_2$ as a testbed

TL;DR

This paper presents a multi-fidelity training procedure for machine learning interatomic potentials that achieves near quantum Monte Carlo accuracy, enabling large-scale simulations of materials like monolayer MoS$_2$ with improved energetics and atomic forces.

Contribution

The authors develop a fine-tuning approach for MLIPs using limited QMC data combined with DFT forces, significantly enhancing accuracy over baseline models.

Findings

The method achieves near QMC accuracy in energy and force predictions.

Limited QMC data suffices to improve DFT-based MLIPs substantially.

Demonstrated on sulfur vacancies in MoS$_2$, the approach accurately predicts migration barriers.

Abstract

We designed a procedure to train a machine learning interatomic potential (MLIP) at benchmark-quality quantum Monte Carlo (QMC) accuracy. To avoid the complexities of high-quality atomic force determination with the stochastic QMC methods, we use a multi-fidelity approach wherein high-level QMC energies are used alongside suitably processed low-level DFT atomic forces to train a QMC fine-tuned MLIP which significantly improves both the energetics and atomic forces over the baseline DFT-based MLIP. Fine-tuning is only applied to the readout layers of an equivariant message-passing MACE MLIP. We used sulfur mono- and multiple vacancies in monolayer MoS$_2$ as a testbed and demonstrate a near QMC accuracy of the model in a number of in- and out-of-domain tests. We show that a fairly limited dataset of QMC energies suffice to significantly improve the baseline DFT MLIP. The accuracy of our approach is demonstrated on energy and free energy migration barriers of mono- and multiple S-vacancy defects. The results open the window to large-scale near QMC quality simulations with large numbers of atoms and/or molecular dynamics configurations which would not be possible by a direct brute-force application of QMC methods.