Artificial neural network potential for Au20clusters based on the first-principles

Lingzhi Cao; Yibo Guo; Wenhua Han; Wenwu Xu; Linwei Sai; Jie Fu

doi:10.1088/1361-648X/ac4f7d

Artificial neural network potential for Au₂₀clusters based on the first-principles

J Phys Condens Matter. 2022 Feb 28;34(17). doi: 10.1088/1361-648X/ac4f7d.

Authors

Lingzhi Cao^{1

2}, Yibo Guo^{1

2}, Wenhua Han², Wenwu Xu², Linwei Sai³, Jie Fu^{1

2}

Affiliations

¹ Institute of High Pressure Physics, School of Physical Science and Technology, Ningbo University, Ningbo 315211, People's Republic of China.
² School of Physical Science and Technology, Ningbo University, Ningbo 315211, People's Republic of China.
³ College of Science, Hohai University, Changzhou 213022, People's Republic of China.

PMID: 35086072
DOI: 10.1088/1361-648X/ac4f7d

Abstract

The search of ground-state structures (GSSs) of gold (Au) clusters is a formidable challenge due to the complexity of potential energy surface (PES). In this work, we have built a high-dimensional artificial neural network (ANN) potential to describe the PES of Au₂₀clusters. The ANN potential is trained through learning the GSS search process of Au₂₀by the combination of density functional theory (DFT) method and genetic algorithm. The root mean square errors of energy and force are 7.72 meV atom^-1and 217.02 meV Å^-1, respectively. As a result, it can find the lowest-energy structure (LES) of Au₂₀clusters that is consistent with previous results. Furthermore, the scalability test shows that it can predict the energy of smaller size Au_16-19clusters with errors less than 22.85 meV atom^-1, and for larger size Au_21-25clusters, the errors are below 36.94 meV atom^-1. Extra attention should be paid to its accuracy for Au_21-25clusters. Applying the ANN to search the GSSs of Au_16-25, we discover two new structures of Au₁₆and Au₂₁that are not reported before and several candidate LESs of Au_16-18. In summary, this work proves that an ANN potential trained for specific size clusters could reproduce the GSS search process by DFT and be applied in the GSS search of smaller size clusters nearby. Therefore, we claim that building ANN potential based on DFT data is one of the most promising ways to effectively accelerate the GSS pre-screening of clusters.

Keywords: artificial neural network; global optimization; gold cluster; ground state structure.