发表机构
Federal University of Parana; Interdisciplinary Center for Science, Technology, and Innovation (CICTI), Federal University of Parana; Imperial College London; University of São Paulo; University of Brasília, Institute of Physics; Zuse Institute Berlin (ZIB)（巴拉那联邦大学; 巴拉那联邦大学跨学科科学技术与创新中心; 帝国理工学院; 圣保罗大学; 巴西利亚大学物理研究所; 柏林祖斯研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对Mn-Ni-Ga Heusler合金中磁态难以从成分直接判定的问题，本文提出基于投影态密度的轨道指纹作为机器学习输入，成功实现磁有序、磁矩、自旋极化分类预测及相图插值，且关键描述符与第一性原理物理一致。
AI 中文摘要
在Mn-Ni-Ga Heusler合金中，竞争性磁态之间的能量差仅为每原子几meV，因此基态必须从电子结构中解析出来，而不能直接从成分读取。偏离化学计量比化合物（在这些化合物中，既定的Heusler磁性规则不再适用）会增加这一难度。为克服此困难，我们引入了从投影态密度中提取的轨道指纹，并将其作为机器学习模型的输入，用于磁有序分类、磁矩幅度预测、费米能级自旋极化预测以及相图插值。模型在涵盖该三元体系的370个准随机结构自旋极化第一性原理计算数据集上训练，这些计算与文献中可获得的磁性基态和晶格参数吻合良好。对于磁有序，排名最高的描述符与第一性原理计算中用于区分各相的量相同，表明这些指纹捕捉到了底层物理机制。
英文摘要
In Mn--Ni--Ga Heusler alloys, the competing magnetic states are separated by differences of a few meV per atom, so the ground state has to be resolved from the electronic structure and cannot be read off the composition. Moving away from the stoichiometric compounds, where the established rules for Heusler magnetism fall short, increases this difficulty. To overcome it, we introduce orbital fingerprints taken from the projected density of states, and use them as the input to machine-learning models for classification of the magnetic ordering, for the magnetic moment amplitude, for the spin polarization at the Fermi level and for interpolation of the phase diagram. The models are trained on a dataset of 370 spin-polarized first-principles calculations of quasirandom structures covering the ternary, which show good agreement with the magnetic ground states and lattice parameters available in the literature. For magnetic ordering, the top-ranked descriptor is the same quantity found by first-principles calculations to distinguish the phases, suggesting that the fingerprints capture the underlying physics.
