Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport

TL;DR

This paper introduces a neuroevolution-based machine learning potential framework that achieves high accuracy and low computational cost for atomistic simulations, enabling efficient heat transport modeling in complex materials.

Contribution

The authors develop a novel NEP framework trained via evolutionary strategies, implemented on GPUs, and capable of simulating heat transport with high efficiency and accuracy.

Findings

Achieves over 10^7 atom-steps per second in MD simulations.

Enables accurate heat transport simulations in disordered materials.

Provides per-atom heat current calculations for thermal analysis.

Abstract

We develop a neuroevolution-potential (NEP) framework for generating neural network based machine-learning potentials. They are trained using an evolutionary strategy for performing large-scale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source GPUMD package, which can attain a computational speed over $10^7$ atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.