arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.01558cond-mat.mtrl-sciphysics.comp-ph
收藏

利用等变神经网络加速磁性体系的电子结构计算

Accelerating the electronic-structure calculation of magnetic systems by equivariant neural networks

Yang Zhong, Binhua Zhang, Hongyu Yu, Xingao Gong, Hongjun Xiang

AI总结:

本文提出等变深度学习框架,直接由磁性构型预测第一性原理 Hamiltonian 矩阵,绕过 DFT 自洽迭代,并在自旋螺旋、非共线反铁磁及数千原子 NiBrI 斯格明子体系中验证了精度与效率。

摘要:

磁体中复杂的自旋—自旋相互作用往往会产生具有复杂局域磁矩排列的磁性超晶格,并且已发现许多此类磁性超晶格具有非平庸的拓扑电子性质。由于磁性超晶格尺寸巨大且磁矩排列复杂,对其直接进行 DFT 计算是一项巨大挑战。本工作设计了一种等变深度学习框架,通过同时利用磁性 Hamiltonian 矩阵的等变约束和自旋—自旋相互作用的物理规律,来加速磁性体系的电子计算。该框架能够绕过代价高昂的自洽迭代,建立从磁性构型到第一性原理 Hamiltonian 矩阵的直接映射。在具有随机磁性构型的磁体上进行训练后,我们的模型在训练集之外的测试结构上取得了很高精度,例如自旋螺旋和非共线反铁磁构型。经过训练的模型还被用于预测包含数千个原子的 NiBrI 斯格明子构型的能带,展示了本模型在大型磁性超晶格上的高效率。

英文摘要:

Complex spin-spin interactions in magnets can often lead to magnetic superlattices with complex local magnetic arrangements, and many of the magnetic superlattices have been found to possess non-trivial topological electronic properties. Due to the huge size and complex magnetic moment arrangement of the magnetic superlattices, it is a great challenge to perform a direct DFT calculation on them. In this work, an equivariant deep learning framework is designed to accelerate the electronic calculation of magnetic systems by exploiting both the equivariant constraints of the magnetic Hamiltonian matrix and the physical rules of spin-spin interactions. This framework can bypass the costly self-consistent iterations and build a direct mapping from a magnetic configuration to the ab initio Hamiltonian matrix. After training on the magnets with random magnetic configurations, our model achieved high accuracy on the test structures outside the training set, such as spin spiral and non-collinear antiferromagnetic configurations. The trained model is also used to predict the energy bands of a skyrmion configuration of NiBrI containing thousands of atoms, showing the high efficiency of our model on large magnetic superlattices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑