Deep Learning Hamiltonians from Disordered Image Data in Quantum Materials

Abstract

The capabilities of image probe experiments are rapidly expanding, providing new information about quantum materials on unprecedented length and time scales. Many such materials feature inhomogeneous electronic properties with intricate pattern formation on the observable surface. This rich spatial structure contains information about interactions, dimensionality, and disorder -- a spatial encoding of the Hamiltonian driving the pattern formation. Image recognition techniques from machine learning are an excellent tool for interpreting information encoded in the spatial relationships in such images. Here, we develop a deep learning framework for using the rich information available in these spatial correlations in order to discover the underlying Hamiltonian driving the patterns. We first vet the method on a known case, scanning near-field optical microscopy on a thin film of VO2. We then apply our trained convolutional neural network architecture to new optical microscope images of a different VO2 film as it goes through the metal-insulator transition. We find that a two-dimensional Hamiltonian with both interactions and random field disorder is required to explain the intricate, fractal intertwining of metal and insulator domains during the transition. This detailed knowledge about the underlying Hamiltonian paves the way to using the model to control the pattern formation via, e.g., tailored hysteresis protocols. We also introduce a distribution-based confidence measure on the results of a multi-label classifier, which does not rely on adversarial training. In addition, we propose a new machine learning based criterion for diagnosing a physical system's proximity to criticality.

References in corpus (37)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• The pseudogap in high-temperature superconductors: an experimental survey
• Complexity in Strongly Correlated Electronic Systems
• Mott transition in VO2 revealed by infrared spectroscopy and nano-imaging
• Machine learning phases of matter
• Big Data of Materials Science - Critical Role of the Descriptor
• A high-bias, low-variance introduction to Machine Learning for physicists
• Electrodynamics of Correlated Electron Materials
• Hysteresis and hierarchies: dynamics of disorder-driven first-order phase transformations
• Progress and perspectives on the electron-doped cuprates
• An Intrinsic Bond-Centered Electronic Glass with Unidirectional Domains in Underdoped Cuprates
• Discovering Phase Transitions with Unsupervised Learning
• Universality and Critical Behavior at the Mott transition
• Explanation of Giant Cluster Coexistence in Doped Manganites and Other Compounds
• Avalanches, Barkhausen Noise, and Plain Old Criticality
• Hysteresis, Avalanches, and Disorder Induced Critical Scaling: A Renormalization Group Approach
• The three-dimensional random field Ising magnet: interfaces, scaling, and the nature of states
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Multiple Avalanches Across the Metal-Insulator Transition of Vanadium Oxide Nano-scaled Junctions
• Machine Learning for Quantum Matter
• Machine learning for many-body physics: The case of the Anderson impurity model
• Universality of pseudogap and emergent order in lightly doped Mott insulators
• Signature of persistent metallic domains in FORC measurements of the VO${}_2$ metal-insulator transition
• Machine Learning for Condensed Matter Physics
• Hysteresis and Noise from Electronic Nematicity in High Temperature Superconductors
• Modeling Electronic Quantum Transport with Machine Learning
• A strongly inhomogeneous superfluid in an iron-based superconductor
• Electrical Breakdown in a V2O3 device at the Insulator to Metal Transition
• Random Field Driven Spatial Complexity at the Mott Transition in VO2
• Universality of liquid-gas Mott transitions at finite temperatures
• Hybrid Machine Learning for Scanning Near-field Optical Spectroscopy
• Scale-invariant magnetic textures in the strongly correlated oxide NdNiO${}_3$
• Deep learning analysis of polaritonic waves images
• Noise Predictions for STM in Systems with Local Electron Nematic Order
• Classifying surface probe images in strongly correlated electronic systems via machine learning
• Quantum Sensing of Insulator-to-Metal Transitions in a Mott Insulator

Cited by in corpus (2)

• Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
• Predicting topological invariants and unconventional superconducting pairing from density of states and machine learning