Detection of Topological Materials with Machine Learning

Abstract

Databases compiled using ab-initio and symmetry-based calculations now contain tens of thousands of topological insulators and topological semimetals. This makes the application of modern machine learning methods to topological materials possible. Using gradient boosted trees, we show how to construct a machine learning model which can predict the topology of a given existent material with an accuracy of 90%. Such predictions are orders of magnitude faster than actual ab-initio calculations. Through extensive testing of different models we determine which properties help detect topological materials. We identify the sources of our model's errors and we discuss approaches to overcome them.

arXiv comment34 pages, 7 figures. The ML model is available online at https://www.topologicalquantumchemistry.com/mltqc. Version 2 includes corrections after peer review

References in corpus (28)

• Scikit-learn: Machine Learning in Python
• Topological Insulators
• Quantum Spin Hall Effect in Graphene
• Quantum Spin Hall Effect and Topological Phase Transition in HgTe Quantum Wells
• $Z_2$ Topological Order and the Quantum Spin Hall Effect
• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Quantized Electric Multipole Insulators
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Topological quantum chemistry
• Colloquium: Topological Band Theory
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• The (High Quality) Topological Materials In The World
• Catalogue of Topological Electronic Materials
• Symmetry-based Indicators of Band Topology in the 230 Space Groups
• Towards ideal topological materials: Comprehensive database searches using symmetry indicators
• Machine learning prediction errors better than DFT accuracy
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Machine learning modeling of superconducting critical temperature
• Fragile Topology and Wannier Obstructions
• Quantitative mappings between symmetry and topology in solids
• Unified Representation of Molecules and Crystals for Machine Learning
• Building Blocks of Topological Quantum Chemistry: Elementary Band Representations
• Wavelet Scattering Regression of Quantum Chemical Energies
• Machine learning spectral indicators of topology

Cited by in corpus (18)

• Provably efficient machine learning for quantum many-body problems
• The 2021 Quantum Materials Roadmap
• Machine learning for materials discovery: two-dimensional topological insulators
• Direct prediction of phonon density of states with Euclidean neural networks
• High-throughput search for magnetic and topological order in transition metal oxides
• Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineering
• Topological thermal transport
• Machine learning spectral indicators of topology
• Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
• Rapid Exploration of Topological Band Structures using Deep Learning
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Discovering two-dimensional magnetic topological insulators by machine learning
• Predicting topological invariants and unconventional superconducting pairing from density of states and machine learning
• Perturbing finite temperature multicomponent DFT 1D Kohn-Sham systems: Peierls Gap & Kohn Anomaly
• Localization of quantum walk with classical randomness: Comparison between manual methods and supervised machine learning
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Exploring exotic configurations with anomalous features using deep learning: Application of classical and quantum-classical hybrid anomaly detection
• Moiré Topology in Twisted Structures with Noncollinear Spin-Orbit Coupling