Back to Search Start Over

Predicting polarizabilities of silicon clusters using local chemical environments

Authors :
Andrew P. Horsfield
Stefano Dal Forno
Mario G. Zauchner
Johannes Lischner
Gábor Cśanyi
Zauchner, Mario G [0000-0002-0901-5642]
Dal Forno, Stefano [0000-0002-9869-7306]
Apollo - University of Cambridge Repository
Publication Year :
2021
Publisher :
Apollo - University of Cambridge Repository, 2021.

Abstract

Calculating polarizabilities of large clusters with first-principles techniques is challenging because of the unfavorable scaling of computational cost with cluster size. To address this challenge, we demonstrate that polarizabilities of large hydrogenated silicon clusters containing thousands of atoms can be efficiently calculated with machine learning methods. Specifically, we construct machine learning models based on the smooth overlap of atomic positions (SOAP) descriptor and train the models using a database of calculated random-phase approximation polarizabilities for clusters containing up to 110 silicon atoms. We first demonstrate the ability of the machine learning models to fit the data and then assess their ability to predict cluster polarizabilities using k-fold cross validation. Finally, we study the machine learning predictions for clusters that are too large for explicit first-principles calculations and find that they accurately describe the dependence of the polarizabilities on the ratio of hydrogen to silicon atoms and also predict a bulk limit that is in good agreement with previous studies.

Details

Database :
OpenAIRE
Accession number :
edsair.doi.dedup.....244ddc598ac1b97005e9305d212dec69
Full Text :
https://doi.org/10.17863/cam.77205