Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure

TL;DR

This study evaluates the transferability of Gaussian process-trained machine learning models for predicting atomic forces in liquid Si and Ge, focusing on temperature and pressure variations, with implications for phase boundary predictions.

Contribution

It demonstrates that ML models trained at high temperatures can effectively transfer to different conditions in liquids, but not to solids, highlighting phase-dependent transferability.

Findings

ML force accuracy drops near phase boundary

High-temperature training improves transferability in liquids

Transferability to solids remains low regardless of training conditions

Abstract

We study a generalization performance of the machine learning (ML) model to predict the atomic forces within the density functional theory (DFT). The targets are the Si and Ge single component systems in the liquid state. To train the machine learning model, Gaussian process regression is performed with the atomic fingerprints which express the local structure around the target atom. The training and test data are generated by the molecular dynamics (MD) based on DFT. We first report the accuracy of ML forces when both test and training data are generated from the DFT-MD simulations at a same temperature. By comparing the accuracy of ML forces at various temperatures, it is found that the accuracy becomes the lowest around the phase boundary between the solid and the liquid states. Furthermore, we investigate the transferability of ML models trained in the liquid state to temperature and pressure. We demonstrate that, if the training is performed at a high temperature and if the volume change is not so large, the transferability of ML forces in the liquid state is high enough, while its transferability to the solid state is very low.