Neural Network Potential from Bispectrum Components: A Case Study on Crystalline Silicon

Authors

Howard Yanxon, University of Nevada, Las VegasFollow
David Zagaceta, University of Nevada, Las VegasFollow
Brandon C. Wood, Lawrence Livermore National Laboratory
Qiang Zhu, University of Nevada, Las VegasFollow

Document Type

Article

Publication Date

8-6-2020

Publication Title

Journal of Chemical Physics

Volume

153

Issue

5

First page number:

1

Last page number:

13

Abstract

In this article, we present a systematic study on developing machine learning force fields (MLFFs) for crystalline silicon. While the main-stream approach of fitting a MLFF is to use a small and localized training set from molecular dynamics simulations, it is unlikely to cover the global features of the potential energy surface. To remedy this issue, we used randomly generated symmetrical crystal structures to train a more general Si-MLFF. Furthermore, we performed substantial benchmarks among different choices of material descriptors and regression techniques on two different sets of silicon data. Our results show that neural network potential fitting with bispectrum coefficients as descriptors is a feasible method for obtaining accurate and transferable MLFFs.

Disciplines

Physical Sciences and Mathematics | Physics

Language

English

Repository Citation

Yanxon, H., Zagaceta, D., Wood, B. C., Zhu, Q. (2020). Neural Network Potential from Bispectrum Components: A Case Study on Crystalline Silicon. Journal of Chemical Physics, 153(5), 1-13.
http://dx.doi.org/10.1063/5.0014677