Machine learning potentials with Iterative Boltzmann Inversion: training to experiment

TL;DR

This paper introduces an iterative correction method for machine learning potentials that integrates experimental data, improving simulation accuracy and addressing overstructuring without complex auto-differentiation or architecture assumptions.

Contribution

The authors propose a novel iterative Boltzmann Inversion approach to incorporate experimental data into MLP training, enhancing model accuracy and predictive capabilities.

Findings

Corrected MLP reduces overstructuring in aluminum melt.

Improved prediction of experimental diffusion constants.

Method does not require auto-differentiation or specific MLP architecture.

Abstract

Methodologies for training machine learning potentials (MLPs) to quantum-mechanical simulation data have recently seen tremendous progress. Experimental data has a very different character than simulated data, and most MLP training procedures cannot be easily adapted to incorporate both types of data into the training process. We investigate a training procedure based on Iterative Boltzmann Inversion that produces a pair potential correction to an existing MLP, using equilibrium radial distribution function data. By applying these corrections to a MLP for pure aluminum based on Density Functional Theory, we observe that the resulting model largely addresses previous overstructuring in the melt phase. Interestingly, the corrected MLP also exhibits improved performance in predicting experimental diffusion constants, which are not included in the training procedure. The presented method does not require auto-differentiating through a molecular dynamics solver, and does not make assumptions about the MLP architecture. The results suggest a practical framework of incorporating experimental data into machine learning models to improve accuracy of molecular dynamics simulations.