arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12630cond-mat.mtrl-sci
收藏

二维材料磁有序性的机器学习研究

Machine Learning Study of the Magnetic Ordering in 2D Materials

Carlos Mera Acosta, Elton Ogoshi, Jose Antonio Souza, Gustavo M. Dalpian

摘要:

磁性材料已应用于从数据存储到量子设备的各种技术中。二维材料的发展为磁性化合物开辟了新的领域,即使经典理论不鼓励他们的检查。在这里,我们提出了一种基于机器学习的策略来预测和理解2D材料中的磁有序。该策略将使用随机森林和SHAP方法预测2D材料中磁性的存在与由预测磁性排序(铁磁或反铁磁)的原子特征定义的材料图相结合。虽然随机森林模型预测磁性的准确度为86%,但通过SISSO方法获得的材料图在预测磁性排序方面的准确度约为90%。我们的模型表明,3D过渡金属,卤化物,和结构集群与常规过渡金属亚晶格有积极的贡献,在总重量决定磁性的存在,在2D化合物。这种行为与晶体场和交换分裂之间的竞争有关。机器学习模型还表明,原子SOC是识别区分铁磁和反铁磁顺序的模式的决定性特征。所提出的策略是用来识别新的二维磁性化合物,连同在化学和结构空间的基本趋势,铺平了新的路线,实验探索。

英文摘要:

Magnetic materials have been applied in a large variety of technologies, from data storage to quantum devices. The development of 2D materials has opened new arenas for magnetic compounds, even when classical theories discourage their examination. Here we propose a machine-learning-based strategy to predict and understand magnetic ordering in 2D materials. This strategy couples the prediction of the existence of magnetism in 2D materials using random forest and the SHAP method with material maps defined by atomic features predicting the magnetic ordering (ferromagnetic or antiferromagnetic). While the random forest model predicts magnetism with an accuracy of 86%, the material maps obtained by the SISSO method have an accuracy of about 90% in predicting the magnetic ordering. Our model indicates that 3d transition metals, halides, and structural clusters with regular transition metals sublattices have a positive contribution in the total weight deciding the existence of magnetism in 2D compounds. This behavior is associated with the competition between crystal field and exchange splitting. The machine learning model also indicates that the atomic SOC is a determinant feature for the identification of the patterns separating ferro- from antiferro-magnetic order. The proposed strategy is used to identify novel 2D magnetic compounds which, together with the fundamental trends in the chemical and structural space, paves novel routes for experimental exploration.

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。

↑