Accurate Thermophysical Properties of Water using Machine-Learned Potentials

TL;DR

This paper demonstrates that equivariant machine-learned potentials, specifically MACE, can accurately predict water's thermophysical properties at DFT-level precision, overcoming previous limitations of speed and reliability.

Contribution

The study introduces the use of equivariant MACE neural networks trained on extensive DFT data to reliably simulate water's thermophysical properties with high accuracy.

Findings

MACE models predict density isobars, diffusion constants, and melting points consistent with DFT.

Equivariant models enable reliable thermodynamic reweighting with minimal bias.

They outperform simpler architectures in accuracy, validating against ground-truth DFT data.

Abstract

Simulating water from first principles remains a significant computational challenge due to the slow dynamics of the underlying system. Although machine-learned interatomic potentials (MLPs) can accelerate these simulations, they often fail to achieve the required level of accuracy for reliable uncertainty quantification. In this study, we use MACE - an equivariant graph neural network architecture that has been trained using an extensive RPBE-D3 database - to predict density isobars, diffusion constants, radial distribution functions, and melting points. Although equivariant MACE models are computationally more expensive than simpler architectures, such as kernel-based potentials (KbPs), their significantly lower total energy errors allow for reliable thermodynamic reweighting with minimal bias. Our results are consistent with those of previous studies using KbPs; however, equivariant models can be validated against the ground-truth density functional theory (DFT) ensemble, providing a critical advantage. These findings establish equivariant MLPs as robust and reliable tools for investigating the thermophysical properties of water with DFT-level accuracy.