Real space mapping of topological invariants using artificial neural networks

Abstract

Topological invariants allow to characterize Hamiltonians, predicting the existence of topologically protected in-gap modes. Those invariants can be computed by tracing the evolution of the occupied wavefunctions under twisted boundary conditions. However, those procedures do not allow to calculate a topological invariant by evaluating the system locally, and thus require information about the wavefunctions in the whole system. Here we show that artificial neural networks can be trained to identify the topological order by evaluating a local projection of the density matrix. We demonstrate this for two different models, a 1-D topological superconductor and a 2-D quantum anomalous Hall state, both with spatially modulated parameters. Our neural network correctly identifies the different topological domains in real space, predicting the location of in-gap states. By combining a neural network with a calculation of the electronic states that uses the Kernel Polynomial Method, we show that the local evaluation of the invariant can be carried out by evaluating a local quantity, in particular for systems without translational symmetry consisting of tens of thousands of atoms. Our results show that supervised learning is an efficient methodology to characterize the local topology of a system.

arXiv comment9 pages, 6 figures

References in corpus (49)

• Topological Insulators
• Topological insulators and superconductors
• Layer-dependent Ferromagnetism in a van der Waals Crystal down to the Monolayer Limit
• Signatures of Majorana fermions in hybrid superconductor-semiconductor nanowire devices
• Majorana Fermions and a Topological Phase Transition in Semiconductor-Superconductor Heterostructures
• Helical liquids and Majorana bound states in quantum wires
• WannierTools: An open-source software package for novel topological materials
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Topological Crystalline Insulators
• Non-Abelian statistics and topological quantum information processing in 1D wire networks
• Intrinsic and Rashba Spin-orbit Interactions in Graphene Sheets
• The Kernel Polynomial Method
• Topological Kondo Insulators
• Machine Learning Unifies the Modelling of Materials and Molecules
• Learning phase transitions by confusion
• Quantum Anomalous Hall Effect in Graphene from Rashba and Exchange Effects
• Topological Mott Insulators
• Computing topological invariants without inversion symmetry
• Proximity-induced ferromagnetism in graphene revealed by anomalous Hall effect
• Z2Pack: Numerical Implementation of Hybrid Wannier Centers for Identifying Topological Materials
• Quantum Entanglement in Neural Network States
• Majorana Fermions in Semiconductor Nanowires
• Ballistic Majorana nanowire devices
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Amorphous topological insulators constructed from random point sets
• Tunable symmetry breaking and helical edge transport in a graphene quantum spin Hall state
• Mapping topological order in coordinate space
• Machine Learning Topological States
• Search for Majorana fermions in multiband semiconducting nanowires
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Machine Learning Phases of Strongly Correlated Fermions
• Second generation Dirac cones and inversion symmetry breaking induced gaps in graphene/hexagonal boron nitride
• Strong magnetization and Chern insulators in compressed graphene/CrI${}_3$ van der Waals heterostructures
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• K-Theory and Pseudospectra for Topological Insulators
• Spontaneous Strains and Gap in Graphene on Boron Nitride
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Aperiodic Weak Topological Superconductors
• Observation of Helical Edge States and Fractional Quantum Hall Effect in a Graphene Electron-hole Bilayer
• Moiré band model and band gaps of graphene on hexagonal boron nitride
• Equivalent topological invariants for one-dimensional Majorana wires in symmetry class D
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Quantum phase recognition via unsupervised machine learning
• Locality of the anomalous Hall conductivity
• Proximity induced quantum anomalous Hall effect in graphene/EuO hetero-structures
• Quantum Hall effect in gapped graphene heterojunctions
• Approaching quantum anomalous Hall effect in proximity-coupled YIG/graphene/h-BN sandwich structure

Cited by in corpus (36)

• Identifying topological order through unsupervised machine learning
• Unsupervised machine learning and band topology
• Machine Learning for Quantum Matter
• Machine Learning for Condensed Matter Physics
• Unsupervised machine learning of topological phase transitions from experimental data
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Computation of topological phase diagram of disordered Pb${}_{1-x}$Sn${}_x$Te using the kernel polynomial method
• Unsupervised Learning of Non-Hermitian Topological Phases
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Machine learning topological phases in real space
• Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites
• Machine learning topological invariants of non-Hermitian systems
• Topological Persistence Machine of Phase Transitions
• Identifying Topological Phase Transitions in Experiments Using Manifold Learning
• Unsupervised learning using topological data augmentation
• Valley notch filter in a graphene strain superlattice: Green's function and machine learning approach
• Application of Convolutional Neural Network to Quantum Percolation in Topological Insulators
• Machine learning non-Hermitian topological phases
• Designing quantum many-body matter with conditional generative adversarial networks
• Probing Chern number by opacity and topological phase transition by a nonlocal Chern marker
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Extracting electronic many-body correlations from local measurements with artificial neural networks
• Hamiltonian learning with real-space impurity tomography in topological moire superconductors
• The repair problem for Reed-Solomon codes: Optimal repair of single and multiple erasures, asymptotically optimal node size
• Neural network enhanced hybrid quantum many-body dynamical distributions
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
• Machine learning of mirror skin effects in the presence of disorder
• A spectrum adaptive kernel polynomial method
• Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
• Quaternion-based machine learning on topological quantum systems
• Effects of electron-electron interactions in the Yu-Shiba-Rusinov lattice model
• Renormalization-group-inspired neural networks for computing topological invariants
• Supervised learning of an interacting 2D hard-core boson model of a weak topological insulator using correlation functions
• Deep learning of topological phase transitions from entanglement aspects: An unsupervised way
• Transfer learning of many-body electronic correlation entropy from local measurements