Machine learning predictions for local electronic properties of disordered correlated electron systems

Abstract

We present a scalable machine learning (ML) model to predict local electronic properties such as on-site electron number and double occupation for disordered correlated electron systems. Our approach is based on the locality principle, or the nearsightedness nature, of many-electron systems, which means local electronic properties depend mainly on the immediate environment. A ML model is developed to encode this complex dependence of local quantities on the neighborhood. We demonstrate our approach using the square-lattice Anderson-Hubbard model, which is a paradigmatic system for studying the interplay between Mott transition and Anderson localization. We develop a lattice descriptor based on group-theoretical method to represent the on-site random potentials within a finite region. The resultant feature variables are used as input to a multi-layer fully connected neural network, which is trained from datasets of variational Monte Carlo (VMC) simulations on small systems. We show that the ML predictions agree reasonably well with the VMC data. Our work underscores the promising potential of ML methods for multi-scale modeling of correlated electron systems.

12 pages, 6 figures

References in corpus (15)

• Deep Learning in Neural Networks: An Overview
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• The Kernel Polynomial Method
• Big Data of Materials Science - Critical Role of the Descriptor
• Machine learning for molecular simulation
• Nearsightedness of Electronic Matter
• Machine learning meets quantum physics
• Critical behavior at Mott-Anderson transition: a TMT-DMFT perspective
• Single-particle excitations under coexisting electron correlation and disorder: a numerical study of the Anderson-Hubbard model
• Electronic Griffiths phase of the d=2 Mott transition
• Disorder-Induced Stabilization of the Pseudogap in Strongly Correlated Systems
• Arrested phase separation in double-exchange models: machine-learning enabled large-scale simulation
• Crystal Structure Representations for Machine Learning Models of Formation Energies
• Local moments and magnetic order in the two-dimensional Anderson-Mott transition
• Descriptors for Machine Learning Model of Generalized Force Field in Condensed Matter Systems

Cited by in corpus (7)

• Convolutional neural networks for large-scale dynamical modeling of itinerant magnets
• Machine learning for phase ordering dynamics of charge density waves
• Machine learning for structure-property relationships: Scalability and limitations
• Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations
• Unsupervised Machine Learning Phase Classification for Falicov-Kimball Model
• Machine-learning force-field models for dynamical simulations of metallic magnets
• Machine learning approach for vibronically renormalized electronic band structures