Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials

Abstract

Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications. The majority of currently known topological materials have been discovered using methods that involve symmetry-based analysis of the quantum wavefunction. Here we use machine learning to develop a simple-to-use heuristic chemical rule that diagnoses with a high accuracy whether a material is topological using only its chemical formula. This heuristic rule is based on a notion that we term topogivity, a machine-learned numerical value for each element that loosely captures its tendency to form topological materials. We next implement a high-throughput procedure for discovering topological materials based on the heuristic topogivity-rule prediction followed by ab initio validation. This way, we discover new topological materials that are not diagnosable using symmetry indicators, including several that may be promising for experimental observation.

Main text: 6 pages, 3 figures; supplementary materials: 43 pages, 62 figures, 5 tables

References in corpus (11)

• 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
• A topological Dirac insulator in a quantum spin Hall phase : Experimental observation of first strong topological insulator
• Topological Crystalline Insulators
• Weyl semimetal phase in non-centrosymmetric transition metal monophosphides
• 3D Dirac semimetals: current materials, design principles and predictions of new materials
• All Topological Bands of All Nonmagnetic Stoichiometric Materials
• Topological quantum materials from the viewpoint of chemistry
• First Principles Calculations for Topological Quantum Materials
• Machine learning for materials discovery: two-dimensional topological insulators

Cited by in corpus (7)

• Topological photonics: fundamental concepts, recent developments, and future directions
• Topological thermal transport
• Multimodal Foundation Models for Material Property Prediction and Discovery
• Discovering two-dimensional magnetic topological insulators by machine learning
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
• Accelerated Discovery of Topological Conductors for Nanoscale Interconnects