Improving the accuracy of the neuroevolution machine learning potential for multi-component systems

In a previous paper Fan et al (2021 Phys. Rev. B 104, 104309), we developed the neuroevolution potential (NEP), a framework of training neural network based machine-learning potentials using a natural evolution strategy and performing molecular dynamics (MD) simulations using the trained potentials. The atom-environment descriptor in NEP was constructed based on a set of radial and angular functions. For multi-component systems, all the radial functions between two atoms are multiplied by some fixed factors that depend on the types of the two atoms only. In this paper, we introduce an improved descriptor for multi-component systems, in which different radial functions are multiplied by different factors that are also optimized during the training process, and show that it can significantly improve the regression accuracy without increasing the computational cost in MD simulations.

Automated summary

This paper presents an improved descriptor for multi-component systems, in which different radial functions are multiplied by optimized factors during the training process. The results show that this approach significantly improves regression accuracy without increasing computational cost in MD simulations.