Prediction of Atomization Energies of Au13+ Clusters through the Machine Learning Approach

TL;DR

This paper introduces a machine learning model that predicts atomization energies of Au13+ clusters efficiently, using descriptors from molecular dynamics data, and improves accuracy by refining descriptor selection.

Contribution

The study presents a novel nonlinear regression approach utilizing interatomic and centroid distances for predicting cluster energies, enhancing computational efficiency over traditional methods.

Findings

Accurately predicted energies for known Au13+ structures.

Improved model performance by removing short-distance descriptors.

Demonstrated effectiveness of machine learning in cluster energy prediction.

Abstract

We examine a new method for predicting the atomization energies of Au13+ clusters by a nonlinear regression model using interatomic and centroid distances as descriptors to improve the efficiency of density-functional theory calculations. Learning data were created using the time-series data of atomic coordinates and Kohn-Sham energy generated by molecular-dynamics simulations. This approach predicted the atomization energies of fifteen known stable/metastable structures of Au13+ clusters well. Moreover, we found that the fitting to the test data could be markedly improved by eliminating the descriptors representing the short interatomic distance.