This study introduces time-reversal E(3)-equivariant neural network and SpinGNN++ framework for constructing a comprehensive interatomic potential for magnetic systems, encompassing spin-orbit coupling and noncollinear magnetic moments. SpinGNN++ integrates multitask spin equivariant neural network with explicit spin-lattice terms, including Heisenberg, Dzyaloshinskii-Moriya, Kitaev, single-ion anisotropy, and biquadratic interactions, and employs time-reversal equivariant neural network to learn high-order spin-lattice interactions using time-reversal E(3)-equivariant convolutions. To validate SpinGNN++, a complex magnetic model dataset is introduced as a benchmark and employed to demonstrate its capabilities. SpinGNN++ provides accurate descriptions of the complex spin-lattice coupling in monolayer CrI$_3$ and CrTe$_2$, achieving sub-meV errors. Importantly, it facilitates large-scale parallel spin-lattice dynamics, thereby enabling the exploration of associated properties, including the magnetic ground state and phase transition. Remarkably, SpinGNN++ identifies a new ferrimagnetic state as the ground magnetic state for monolayer CrTe2, thereby enriching its phase diagram and providing deeper insights into the distinct magnetic signals observed in various experiments.
Scalable Dielectric Tensor Predictions for Inorganic Materials using Equivariant Graph Neural Networks
The Hong Kong Polytechnic University(香港理工大学);The University of Tokyo(东京大学);Hong Kong University of Science and Technology(香港科技大学);The Chinese University of Hong Kong(香港中文大学);National Institute for Materials Science(国立研究开发法人物质·材料研究机构);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能研究中心)
Equivariant Many-body Message Passing Interatomic Potentials for Magnetic Materials
University of British Columbia(不列颠哥伦比亚大学);Symmetric Group(对称集团);MatNex;University of Cambridge(剑桥大学);Max Planck Institute for Polymer Research(马克斯·普朗克高分子研究所)
Universal Hamiltonian learning with rotational and basis equivariance
Tsinghua University(清华大学);Chen-Ning Yang Institute for Advanced Study, Tsinghua University(清华大学陈省身高等研究院);Frontier Science Center for Quantum Information(量子信息前沿科学中心)
E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
Harvard University(哈佛大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Robert Bosch Research and Technology Center(罗伯特·博世研究与技术中心);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Massachusetts Institute of Technology(麻省理工学院)
Department of Applied Mathematics(应用数学系);Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark(计算机科学,丹麦技术大学,Kongens Lyngby);Department of Physics, Technical University of Denmark, Kongens Lyngby, Denmark(物理系,丹麦技术大学,Kongens Lyngby)
EAC-Net: Predicting real-space charge density via equivariant atomic contributions
Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences(中国科学院宁波材料技术与工程研究所);Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州高等研究院);School of Artificial Intelligence and Data Science, University of Science and Technology of China(中国科学技术大学人工智能与数据科学学院);College of Materials Science and Opto-Electronic Technology, University of Chinese Academy of Sciences(中国科学院大学材料科学与光电技术学院);Suzhou Lab, Suzhou, Jiangsu, China(苏州实验室)
First order reversal curves and intrinsic parameter determination for magnetic materials; limitations of hysteron-based approaches in correlated systems
Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
Department of Mechanical Engineering, Texas Tech University, Lubbock, Texas 79409, USA(德克萨斯理工大学机械工程系);Samsung Advanced Institute of Technology, Samsung Electronics, Suwon 16678, Republic of Korea(三星电子首尔先进技术研究所)
Learning local equivariant representations for quantum operators
AI for Science Institute(北京智源人工智能研究院);McGill University(麦吉尔大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);Birla Institute of Technology & Science, Pilani-Dubai Campus(毕拉理工与科学学院 Pilani 迪拜校区);DP Technology(深势科技);University of Science and Technology of China(中国科学技术大学);Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州高等研究院)
Time reversal symmetry breaking superconductivity in topological materials
已经知道,快速现象是由描述具有线性色散关系的高能粒子的相对论性量子力学的狄拉克理论引起的。固体中的电子通常具有非相对论色散关系,但它们的量子激发可以模拟相对论效应。在拓扑绝缘体中,电子在表面上具有线性色散关系,即狄拉克行为,而在本体中具有非相对论性能量色散。物质的拓扑相,特别是拓扑绝缘体材料中的对称性破缺相引起了人们的广泛兴趣。在这里,我们报告的Nb掺杂的拓扑绝缘体Bi 2 Se 3可以变成一个块体II型超导体,而在正常状态下的狄拉克表面色散被保存。在超导临界温度3.2 K以下出现宏观磁有序,表明Nb的磁矩发生自发自旋旋转对称破缺.尽管这种磁序可能出现在超导体的边缘,但它是由超导性介导的,并呈现出一种新的物质相,从而产生零场霍尔效应。
Fast and Accurate Equivariant Foundation Models for Atomistic Simulation
Yusuf Hamied Department of Chemistry, University of Cambridge(剑桥大学);John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学);Department of Materials Science and Engineering, Massachusetts Institute of Technology(麻省理工学院);Department of Molecular Science and Software Engineering, University of California, Berkeley(加州大学伯克利分校);Sandia National Laboratories(桑迪亚国家实验室)
Department of Materials Science & Engineering, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校材料科学与工程系);Department of Computer Science, Princeton University(普林斯顿大学计算机科学系);Materials Research Laboratory, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校材料研究实验室)
Towards understanding of magnetization reversal in Nd$-$Fe$-$B nanocomposites: Analysis by high-throughput micromagnetic simulations
我们演示了如何微磁模拟可以用来表征和分析纳米复合材料的磁性微结构。以纳米晶Nd $-$ Fe $-$ B为例,这是一种未来永磁应用的潜在材料,我们比较了这类材料的微磁学分析的三种不同模型:(i)根据Stoner-Wohlfarth颗粒有和没有磁偶极相互作用的纳米复合微结构的描述;(ii)基于纳米颗粒的核-壳表示的模型;(iii)后一种模型包括超顺磁性团簇的贡献。相关的参数空间进行了系统的扫描,目的是建立微磁方法可以最充分地描述这种材料的实验数据。根据我们的研究结果,只有最后,最复杂的模型是能够提供一个很好的协议与测得的磁滞回线。所提出的方法是普遍适用于多相磁性纳米复合材料,它highlighths的微观结构,磁相互作用和宏观磁性能之间的复杂的相互关系。
Machine learning Hubbard parameters with equivariant neural networks
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学);University of California Berkeley(加州大学伯克利分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Paul Scherrer Institut (PSI)(保罗·谢勒研究所)
Effects of Interactions and Defect Motion on Ramp Reversal Memory in Locally Phase Separated Materials
Purdue University(普渡大学);Purdue Quantum Science and Engineering Institute(普渡量子科学与工程研究所);ESPCI Paris(巴黎高等物理化工学院);Sorbonne Université(索邦大学);University of Denver(丹佛大学);University of California-San Diego(加州大学圣地亚哥分校)