High-dimensional neural network atomic potentials for examining energy materials: some recent simulations

Owing to their simultaneous accuracy and computational efficiency, interatomic potentials machine-learned using first-principles calculation data are promising for investigating phenomena closely related to atomic motion in various energy materials. We have been working with one type of these potent...

Full description

Saved in:
Bibliographic Details
Published inJPhys Energy Vol. 3; no. 1; pp. 12003 - 12018
Main Authors Watanabe, Satoshi, Li, Wenwen, Jeong, Wonseok, Lee, Dongheon, Shimizu, Koji, Mimanitani, Emi, Ando, Yasunobu, Han, Seungwu
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.01.2021
Subjects
Data sampling
First principles
Ion migration
machine learning
Mapping
neural network
Neural networks
Nuclear energy
thermal transport
Online AccessGet full text

Cover

More Information
Summary:Owing to their simultaneous accuracy and computational efficiency, interatomic potentials machine-learned using first-principles calculation data are promising for investigating phenomena closely related to atomic motion in various energy materials. We have been working with one type of these potentials, high-dimensional (HD) neural network potentials (NNPs), and their applications, but we realized that our current understanding of HD NNPs, e.g. the meaning of the atomic energy mapping, remained insufficient, and that tuning their prediction performance for different target properties/phenomena often requires much trial and error. In this article, we illustrate the usefulness of NNPs through our studies on ion migration and thermal transport in energy and related materials. We also share our experiences with data sampling and training strategies and discuss the meaning of atomic energy mapping in HD NNPs.
Bibliography:JPENERGY-100288.R2
ISSN:2515-7655
2515-7655
DOI:10.1088/2515-7655/abc7f3