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

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.

Automated summary

In this research, a neuroevolution-potential framework for generating neural network-based machine-learning potentials trained with an evolutionary strategy is developed. The atomic environment descriptor is constructed using Chebyshev and Legendre polynomials. The NEP method, implemented in GPUMD package, achieves high computational speed and provides per-atom heat current information.