Machine Learning Study of the Magnetic Ordering in 2D Materials

Abstract

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.

arXiv comment31 pages, 12 figures

References in corpus (30)

• Electric Field Effect in Atomically Thin Carbon Films
• Magic-angle graphene superlattices: a new platform for unconventional superconductivity
• Layer-dependent Ferromagnetism in a van der Waals Crystal down to the Monolayer Limit
• Discovery of intrinsic ferromagnetism in 2D van der Waals crystals
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Two-Dimensional Itinerant Ising Ferromagnetism in Atomically thin Fe3GeTe2
• The Computational 2D Materials Database: High-Throughput Modeling and Discovery of Atomically Thin Crystals
• Controlling magnetism in 2D CrI3 by electrostatic doping
• Ising-Type Magnetic Ordering in Atomically Thin FePS3
• Probing magnetism in 2D van der Waals crystalline insulators via electron tunneling
• Big Data of Materials Science - Critical Role of the Descriptor
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Room Temperature Intrinsic Ferromagnetism in Epitaxial Manganese Selenide Films in the Monolayer Limit
• Robust Intrinsic Ferromagnetism and Half Semiconductivity in Stable Two-Dimensional Single-Layer Chromium Trihalides
• Stacking-Dependent Magnetism in Bilayer CrI${}_3$
• On the origin of magnetic anisotropy in two dimensional CrI${}_3$
• Recent Progress of the Computational 2D Materials Database (C2DB)
• Suppression of magnetic ordering in XXZ-type antiferromagnetic monolayer NiPS3
• Evolution of interlayer and intralayer magnetism in three atomically thin chromium trihalides
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• Antiferromagnetic ordering in van der Waals two-dimensional magnetic material MnPS3 probed by Raman spectroscopy
• Van der Waals spin valves
• Band structure model of magnetic coupling in semiconductors
• Learning physical descriptors for materials science by compressed sensing
• High throughput computational screening for 2D ferromagnetic materials: the critical role of anisotropy and local correlations
• High throughput computational screening for two-dimensional magnetic materials based on experimental databases of three-dimensional compounds
• Predicting the Curie temperature of ferromagnets using machine learning
• Electronic structure and magnetism in two-dimensional hexagonal 5d transition metal carbides, Tan+1Cn (n=1,2,3)
• Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites

Cited by in corpus (8)

• Phyllosilicates as earth-abundant layered materials for electronics and optoelectronics: Prospects and challenges in their ultrathin limit
• Hidden orders in spin-orbit entangled correlated insulators
• High throughput inverse design and Bayesian optimization of functionalities: spin splitting in two-dimensional compounds
• The Northeast Materials Database for Magnetic Materials
• Classification of magnetic order from electronic structure by using machine learning
• A New Workflow for Materials Discovery Bridging the Gap Between Experimental Databases and Graph Neural Networks
• Computational Frameworks for Patterned Two-Dimensional Magnetism
• Stacking-dependent magnetic ordering in bilayer ScI${}_2$