Equivariant Neural Network Force Fields for Magnetic Materials

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yuan, Zilong, Xu, Zhiming, Li, He, Cheng, Xinle, Tao, Honggeng, Tang, Zechen, Zhou, Zhiyuan, Duan, Wenhui, Xu, Yong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914670114242560
author Yuan, Zilong
Xu, Zhiming
Li, He
Cheng, Xinle
Tao, Honggeng
Tang, Zechen
Zhou, Zhiyuan
Duan, Wenhui
Xu, Yong
author_facet Yuan, Zilong
Xu, Zhiming
Li, He
Cheng, Xinle
Tao, Honggeng
Tang, Zechen
Zhou, Zhiyuan
Duan, Wenhui
Xu, Yong
contents Neural network force fields have significantly advanced ab initio atomistic simulations across diverse fields. However, their application in the realm of magnetic materials is still in its early stage due to challenges posed by the subtle magnetic energy landscape and the difficulty of obtaining training data. Here we introduce a data-efficient neural network architecture to represent density functional theory total energy, atomic forces, and magnetic forces as functions of atomic and magnetic structures. Our approach incorporates the principle of equivariance under the three-dimensional Euclidean group into the neural network model. Through systematic experiments on various systems, including monolayer magnets, curved nanotube magnets, and moiré-twisted bilayer magnets of $\text{CrI}_{3}$, we showcase the method's high efficiency and accuracy, as well as exceptional generalization ability. The work creates opportunities for exploring magnetic phenomena in large-scale materials systems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04864
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Equivariant Neural Network Force Fields for Magnetic Materials
Yuan, Zilong
Xu, Zhiming
Li, He
Cheng, Xinle
Tao, Honggeng
Tang, Zechen
Zhou, Zhiyuan
Duan, Wenhui
Xu, Yong
Materials Science
Neural network force fields have significantly advanced ab initio atomistic simulations across diverse fields. However, their application in the realm of magnetic materials is still in its early stage due to challenges posed by the subtle magnetic energy landscape and the difficulty of obtaining training data. Here we introduce a data-efficient neural network architecture to represent density functional theory total energy, atomic forces, and magnetic forces as functions of atomic and magnetic structures. Our approach incorporates the principle of equivariance under the three-dimensional Euclidean group into the neural network model. Through systematic experiments on various systems, including monolayer magnets, curved nanotube magnets, and moiré-twisted bilayer magnets of $\text{CrI}_{3}$, we showcase the method's high efficiency and accuracy, as well as exceptional generalization ability. The work creates opportunities for exploring magnetic phenomena in large-scale materials systems.
title Equivariant Neural Network Force Fields for Magnetic Materials
topic Materials Science
url https://arxiv.org/abs/2402.04864