High temperature melting of dense molecular hydrogen from machine-learning interatomic potentials trained on quantum Monte Carlo

TL;DR

This paper develops a machine learning model trained on quantum Monte Carlo data to accurately predict the melting temperature and phase behavior of dense molecular hydrogen under high pressure, integrating advanced methods for improved precision.

Contribution

It introduces a novel machine learning approach trained on quantum Monte Carlo data, combined with a two-phase method and Clausius-Clapeyron estimates for precise melting curve predictions.

Findings

Predicted melting temperatures from 50 GPa to 180 GPa.

Identified molecular dissociation at high pressures.

Achieved close agreement with experimental data.

Abstract

We present results and discuss methods for computing the melting temperature of dense molecular hydrogen using a machine learned model trained on quantum Monte Carlo data. In this newly trained model, we emphasize the importance of accurate total energies in the training. We integrate a two phase method for estimating the melting temperature with estimates from the Clausius-Clapeyron relation to provide a more accurate melting curve from the model. We make detailed predictions of the melting temperature, solid and liquid volumes, latent heat and internal energy from 50 GPa to 180 GPa for both classical hydrogen and quantum hydrogen. At pressures of roughly 173 GPa and 1635K, we observe molecular dissociation in the liquid phase. We compare with previous simulations and experimental measurements.