Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
arXiv:2302.12274 · doi:10.1038/s41467-023-40684-1
Abstract
Modern scanning probe techniques, like scanning tunneling microscopy (STM), provide access to a large amount of data encoding the underlying physics of quantum matter. In this work, we analyze how convolutional neural networks (CNN) can be employed to learn effective theoretical models from STM data on correlated moiré superlattices. These engineered systems are particularly well suited for this task as their enhanced lattice constant provides unprecedented access to intra-unit-cell physics and their tunability allows for high-dimensional data sets within a single sample. Using electronic nematic order in twisted double-bilayer graphene (TDBG) as an example, we show that including correlations between the local density of states (LDOS) at different energies allows CNNs not only to learn the microscopic nematic order parameter, but also to distinguish it from heterostrain. These results demonstrate that neural networks constitute a powerful methodology for investigating the microscopic details of correlated phenomena in moiré systems and beyond.
arXiv comment10+7 pages, 5+6 figures
References in corpus (52)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Magic-angle graphene superlattices: a new platform for unconventional superconductivity
- Quantum Spin Hall Effect in Graphene
- Correlated Insulator Behaviour at Half-Filling in Magic Angle Graphene Superlattices
- Machine learning and the physical sciences
- Emergent ferromagnetism near three-quarters filling in twisted bilayer graphene
- Nematic order in iron superconductors - who is in the driver's seat?
- Intrinsic and Rashba Spin-orbit Interactions in Graphene Sheets
- Magic Angle Spectroscopy
- Graphene Bilayers with a Twist
- Imaging Electronic Correlations in Twisted Bilayer Graphene near the Magic Angle
- Electric Field Tunable Correlated States and Magnetic Phase Transitions in Twisted Bilayer-Bilayer Graphene
- Charge-Order and Broken Rotational Symmetry in Magic Angle Twisted Bilayer Graphene
- Nematic Fermi Fluids in Condensed Matter Physics
- Spin-polarized Correlated Insulator and Superconductor in Twisted Double Bilayer Graphene
- Correlated states in twisted double bilayer graphene
- Nematicity and Competing Orders in Superconducting Magic-Angle Graphene
- Zero-field superconducting diode effect in small-twist-angle trilayer graphene
- Experimental Quantum Hamiltonian Learning
- Designing Flat Band by Strain
- Tuning electron correlation in magic-angle twisted bilayer graphene using Coulomb screening
- Hamiltonian Learning and Certification Using Quantum Resources
- Robust Online Hamiltonian Learning
- Strain-induced Evolution of Electronic Band Structures in a Twisted Graphene Bilayer
- Band structure and topological property of twisted double bilayer graphenes
- Electronic spectrum of twisted graphene layers under heterostrain
- Machine Learning in Electronic Quantum Matter Imaging Experiments
- Classifying Snapshots of the Doped Hubbard Model with Machine Learning
- Universal moiré nematic phase in twisted graphitic systems
- Electronic multicriticality in bilayer graphene
- Imaging inter-valley coherent order in magic-angle twisted trilayer graphene
- Superconductivity in Twisted Double Bilayer Graphene Stabilized by WSe
- Hamiltonian Learning for Quantum Error Correction
- Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images
- Spontaneous time-reversal symmetry breaking in twisted double bilayer graphene
- Robust and Efficient Hamiltonian Learning
- Limits on dynamically generated spin-orbit coupling: Absence of Pomeranchuk instabilities in metals
- Electric-field-tunable electronic nematic order in twisted double-bilayer graphene
- Untrained physically informed neural network for image reconstruction of magnetic field sources
- Strain-induced modulation of Dirac cones and van Hove singularities in twisted graphene bilayer
- Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
- Non-coplanar magnetism, topological density wave order and emergent symmetry at half-integer filling of moiré Chern bands
- Removing grid structure in angle-resolved photoemission spectra via deep learning method
- Classifying surface probe images in strongly correlated electronic systems via machine learning
- Machine Learning Identification of Impurities in the STM Images
- Detecting Nematic Order in STM/STS Data with Artificial Intelligence
- Deep Learning Hamiltonians from Disordered Image Data in Quantum Materials
- Machine-learning the spectral function of a hole in a quantum antiferromagnet
- Learning crystal field parameters using convolutional neural networks
- Unsupervised learning of two-component nematicity from STM data on magic angle bilayer graphene
- Machine Learning for Optical Scanning Probe Nanoscopy
Cited by in corpus (7)
- Enhanced Superconducting Diode Effect due to coexisting Phases
- Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
- Hamiltonian learning with real-space impurity tomography in topological moire superconductors
- Predicting topological invariants and unconventional superconducting pairing from density of states and machine learning
- Displacement-field-tunable superconductivity in an inversion-symmetric twisted van der Waals heterostructure
- Moiré spintronics: Emergent phenomena, material realization and machine learning accelerating discovery
- Prediction of the Hubbard U parameter from scanning tunneling microscopy images of moire systems using image recognition