Rapid Exploration of Topological Band Structures using Deep Learning

Abstract

The design of periodic nanostructures allows to tailor the transport of photons, phonons, and matter waves for specific applications. Recent years have seen a further expansion of this field by engineering topological properties. However, what is missing currently are efficient ways to rapidly explore and optimize band structures and to classify their topological characteristics, for arbitrary unit cell geometries. In this work, we show how deep learning can address this challenge. We introduce an approach where a neural network first maps the geometry to a tight-binding model. This allows us to exploit any underlying space group and predict the symmetries of Bloch waves. We demonstrate how that helps to rapidly categorize a large set of geometries in terms of their band representations, identifying designs for fragile topologies. Engineering of domain walls and optimization are also accelerated by orders of magnitude. The approach is general enough to permit future applications to the geometry discovery in other classes of materials (e.g. active and nonlinear metamaterials).

Strongly expanded version including more case studies and demonstration of Chern number prediction

References in corpus (25)

• Quantum Spin Hall Effect and Topological Phase Transition in HgTe Quantum Wells
• Quantum Spin Hall Insulator State in HgTe Quantum Wells
• Topological Photonics
• SchNet - a deep learning architecture for molecules and materials
• Scheme to Achieve Silicon Topological Photonics
• The (High Quality) Topological Materials In The World
• Topological Bands for Ultracold Atoms
• A topological quantum optics interface
• Bulk Topological Invariants in Noninteracting Point Group Symmetric Insulators
• Faithful Tight-binding Models and Fragile Topology of Magic-angle Bilayer Graphene
• Fragile Topology and Wannier Obstructions
• Building Blocks of Topological Quantum Chemistry: Elementary Band Representations
• Experimental realization of on-chip topological nanoelectromechanical metamaterials
• Optimization of photonic crystal nanocavities based on deep learning
• Topological Photonic Quasicrystals: Fractal Topological Spectrum and Protected Transport
• Learning with Known Operators reduces Maximum Training Error Bounds
• Experimental characterization of fragile topology in an acoustic metamaterial
• Topological Insulators by Topology Optimization
• Robust topology optimization of three-dimensional photonic-crystal band-gap structures
• Engineering Fragile Topology in Photonic Crystals: Topological Quantum Chemistry of Light
• Deep Learning Topological Invariants of Band Insulators
• Band Connectivity for Topological Quantum Chemistry: Band Structures As A Graph Theory Problem
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Detection of Topological Materials with Machine Learning
• Divergence of predictive model output as indication of phase transitions

Cited by in corpus (9)

• Provably efficient machine learning for quantum many-body problems
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networks
• Greedy optimization of the geometry of Majorana Josephson junctions
• Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene
• Energy density as a probe of band representations in photonic crystals
• Efficient and quantum-adaptive machine learning with fermion neural networks
• Dual-Capability Machine Learning Models for Quantum Hamiltonian Parameter Estimation and Dynamics Prediction
• A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes