Towards a universal model for spin–orbit physics

doi:10.1038/s42256-026-01221-z

2026-04-20

PRE

Atul C. Thakur

Shyue Ping Ong *

DOI：10.1038/s42256-026-01221-z

原文链接

原文求助

摘要

En 中文

一种新型机器学习框架预测全周期表范围内的自旋-轨道耦合电子结构，实现量子材料的高通量探索

Keyword:

Computational methods

Magnetic properties and materials

Engineering

general

期刊

Nature Machine Intelligence

IF:

23.9

论文数:

1.3K

被引数:

1.5W

机构

university of california

学者数:

1.9W

论文数: 8.0K

被引数: 10

引用论文

Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation 用于有效从头算电子结构计算的深度学习密度泛函理论哈密顿量

NATURE COMPUTATIONAL SCIENCE

IF18.3

2022-06-23

OAAI

Li, He; Wang, Zun; Zou, Nianlong; Ye, Meng; Xu, Runzhang; Gong, Xiaoxun; Duan, Wenhui; Xu, Yong

Spin tunnel field-effect transistors based on two-dimensional van der Waals heterostructures

NATURE ELECTRONICS

IF40.9

2019-04-15

236

PREAI

Jiang, Shengwei; Li, Lizhong; Wang, Zefang; Shan, Jie; Mak, Kin Fai

General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian

NATURE COMMUNICATIONS

IF15.7

2023-05-18

OAAI

Gong, Xiaoxun; Li, He; Zou, Nianlong; Xu, Runzhang; Duan, Wenhui; Xu, Yong

A universal spin–orbit-coupled Hamiltonian model for accelerated quantum material discovery 用于加速量子材料发现的通用自旋轨道耦合哈密顿模型

Nature Machine Intelligence

IF23.9

2026-02-27

PREAI

Yang Zhong; Rui Wang; Xingao Gong; Hongjun Xiang