RESUMO
The development of spintronic devices demands the existence of materials with some kind of spin splitting (SS). In this Data Descriptor, we build a database of ab initio calculated SS in 2D materials. More than that, we propose a workflow for materials design integrating an inverse design approach and a Bayesian inference optimization. We use the prediction of SS prototypes for spintronic applications as an illustrative example of the proposed workflow. The prediction process starts with the establishment of the design principles (the physical mechanism behind the target properties), that are used as filters for materials screening, and followed by density functional theory (DFT) calculations. Applying this process to the C2DB database, we identify and classify 358 2D materials according to SS type at the valence and/or conduction bands. The Bayesian optimization captures trends that are used for the rationalized design of 2D materials with the ideal conditions of band gap and SS for potential spintronics applications. Our workflow can be applied to any other material property.
RESUMO
Magnetic materials have been applied in a large variety of technologies, from data storage to quantum devices. The development of two-dimensional (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 a random forest and the Shapley additive explanations 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 sure independence screening and sparsifying method have an accuracy of â¼90% in predicting the magnetic ordering. Our model indicates that 3d transition metals, halides, and structural clusters with regular transition-metal 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 spin orbit coupling (SOC) is a determinant feature for the identification of the patterns separating ferro- from antiferromagnetic order. The proposed strategy is used to identify novel 2D magnetic compounds that, together with the fundamental trends in the chemical and structural space, pave novel routes for experimental exploration.