Predicting hot-electron free energies from ground-state data

TL;DR

This paper introduces a machine-learning method to predict electronic free energies at various temperatures using only ground-state data, enabling improved modeling of metals and warm dense matter without temperature-specific training.

Contribution

The authors develop a hybrid approach that combines physical principles with machine learning to estimate temperature-dependent free energies from ground-state data alone.

Findings

Successfully benchmarked on metallic liquid hydrogen under astrophysical conditions.

Demonstrated the method's ability to predict free energies at arbitrary electron temperatures.

Showed advantages of hybrid physics-data driven schemes in atomistic modeling.

Abstract

Machine-learning potentials are usually trained on the ground-state, Born-Oppenheimer energy surface, which depends exclusively on the atomic positions and not on the simulation temperature. This disregards the effect of thermally-excited electrons, that is important in metals, and essential to the description of warm dense matter. An accurate physical description of these effects requires that the nuclei move on a temperature-dependent electronic free energy. We propose a method to obtain machine-learning predictions of this free energy at an arbitrary electron temperature using exclusively training data from ground-state calculations, avoiding the need to train temperature-dependent potentials, and benchmark it on metallic liquid hydrogen at the conditions of the core of gas giants and brown dwarfs. This work demonstrates the advantages of hybrid schemes that use physical consideration to combine machine-learning predictions, providing a blueprint for the development of similar approaches that extend the reach of atomistic modelling by removing the barrier between physics and data-driven methodologies.