Discovering two-dimensional magnetic topological insulators by machine learning

Abstract

Topological materials with unconventional electronic properties have been investigated intensively for both fundamental and practical interests. Thousands of topological materials have been identified by symmetry-based analysis and ab initio calculations. However, the predicted magnetic topological insulators with genuine full band gaps are rare. Here we employ this database and supervisedly train neural networks to develop a heuristic chemical rule for electronic topology diagnosis. The learned rule is interpretable and diagnoses with a high accuracy whether a material is topological using only its chemical formula and Hubbard $U$ parameter. We next evaluate the model performance in several different regimes of materials. Finally, we integrate machine-learned rule with ab initio calculations to high-throughput screen for magnetic topological insulators in 2D material database. We discover 6 new classes (15 materials) of Chern insulators, among which 4 classes (7 materials) have full band gaps and may motivate for experimental observation. We anticipate the machine-learned rule here can be used as a guiding principle for inverse design and discovery of new topological materials.

7 pages, 4 figures

References in corpus (12)

• Quantum Spin Hall Effect and Topological Phase Transition in HgTe Quantum Wells
• Quantum Spin Hall Insulator State in HgTe Quantum Wells
• Topological Insulators with Inversion Symmetry
• Topological Crystalline Insulators
• Bulk Topological Invariants in Noninteracting Point Group Symmetric Insulators
• Progress and prospects in magnetic topological materials
• Topological quantum materials from the viewpoint of chemistry
• NiCl3 Monolayer: Dirac Spin-Gapless Semiconductor and Chern Insulator
• Machine learning for materials discovery: two-dimensional topological insulators
• Two-dimensional antiferromagnetic Dirac fermions in monolayer TaCoTe${}_2$
• Intrinsic large gap quantum anomalous Hall insulators in La$X$ ($X$=Br, Cl, I)
• Discovery of a magnetic Dirac system with large intrinsic non-linear Hall effect

Cited by in corpus (4)

• Intrinsic antiferromagnetic topological insulator and axion state in V2WS4
• Enhancing Large Language Models with Domain-Specific Knowledge: The Case in Topological Materials
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Design, synthesis, and physical properties of the intergrowth compound Eu${}_2$CuZn${}_2$As${}_3$