Saved in:
Bibliographic Details
Main Authors: Zheng, Daye, Peng, Xingliang, Huang, Yike, Wang, Yinan, Zhang, Duo, Huang, Zhengtao, Cai, Zefeng, Zhang, Linfeng, Chen, Mohan, Xu, Ben, Zhou, Weiqing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.14382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912755887374336
author Zheng, Daye
Peng, Xingliang
Huang, Yike
Wang, Yinan
Zhang, Duo
Huang, Zhengtao
Cai, Zefeng
Zhang, Linfeng
Chen, Mohan
Xu, Ben
Zhou, Weiqing
author_facet Zheng, Daye
Peng, Xingliang
Huang, Yike
Wang, Yinan
Zhang, Duo
Huang, Zhengtao
Cai, Zefeng
Zhang, Linfeng
Chen, Mohan
Xu, Ben
Zhou, Weiqing
contents We propose a non-collinear spin-constrained method that generates training data for deep-learning-based magnetic model, which provides a powerful tool for studying complex magnetic phenomena that requires large-scale simulations at the atomic level. First, we propose a basis-independent projection method for calculating atomic magnetic moments by applying a radial truncation to numerical atomic orbitals. A double-loop Lagrange multiplier method is utilized to ensure the satisfaction of constraint conditions while achieving accurate magnetic torque. The method is implemented in ABACUS with both plane wave basis and numerical atomic orbital basis. We benchmark the iron (Fe) systems and analyze differences from calculations with the plane wave basis and numerical atomic orbitals basis in describing magnetic energy barriers. Based on an automated workflow composed of first-principles calculations, magnetic model, active learning, and dynamics simulation, more than 30,000 first-principles data with the information of magnetic torque are generated to train a deep-learning-based magnetic model DeePSPIN for the Fe system. By utilizing the model in large-scale molecular dynamics simulations, we successfully predict Curie temperatures of alpha-Fe close to experimental values.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Integrating Deep-Learning-Based Magnetic Model and Non-Collinear Spin-Constrained Method: Methodology, Implementation and Application
Zheng, Daye
Peng, Xingliang
Huang, Yike
Wang, Yinan
Zhang, Duo
Huang, Zhengtao
Cai, Zefeng
Zhang, Linfeng
Chen, Mohan
Xu, Ben
Zhou, Weiqing
Materials Science
We propose a non-collinear spin-constrained method that generates training data for deep-learning-based magnetic model, which provides a powerful tool for studying complex magnetic phenomena that requires large-scale simulations at the atomic level. First, we propose a basis-independent projection method for calculating atomic magnetic moments by applying a radial truncation to numerical atomic orbitals. A double-loop Lagrange multiplier method is utilized to ensure the satisfaction of constraint conditions while achieving accurate magnetic torque. The method is implemented in ABACUS with both plane wave basis and numerical atomic orbital basis. We benchmark the iron (Fe) systems and analyze differences from calculations with the plane wave basis and numerical atomic orbitals basis in describing magnetic energy barriers. Based on an automated workflow composed of first-principles calculations, magnetic model, active learning, and dynamics simulation, more than 30,000 first-principles data with the information of magnetic torque are generated to train a deep-learning-based magnetic model DeePSPIN for the Fe system. By utilizing the model in large-scale molecular dynamics simulations, we successfully predict Curie temperatures of alpha-Fe close to experimental values.
title Integrating Deep-Learning-Based Magnetic Model and Non-Collinear Spin-Constrained Method: Methodology, Implementation and Application
topic Materials Science
url https://arxiv.org/abs/2501.14382