Machine learning approach for vibronically renormalized electronic band structures

Abstract

We present a machine learning (ML) method for efficient computation of vibrational thermal expectation values of physical properties from first principles. Our approach is based on the non-perturbative frozen phonon formulation in which stochastic Monte Carlo algorithm is employed to sample configurations of nuclei in a supercell at finite temperatures based on a first-principles phonon model. A deep-learning neural network is trained to accurately predict physical properties associated with sampled phonon configurations, thus bypassing the time-consuming {\em ab initio} calculations. To incorporate the point-group symmetry of the electronic system into the ML model, group-theoretical methods are used to develop a symmetry-invariant descriptor for phonon configurations in the supercell. We apply our ML approach to compute the temperature dependent electronic energy gap of silicon based on density functional theory (DFT). We show that, with less than a hundred DFT calculations for training the neural network model, an order of magnitude larger number of sampling can be achieved for the computation of the vibrational thermal expectation values. Our work highlights the promising potential of ML techniques for finite temperature first-principles electronic structure methods.

17 pages, 7 figures

References in corpus (48)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Phonons and related properties of extended systems from density-functional perturbation theory
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• The GW method
• Electron-phonon interactions from first principles
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Big Data of Materials Science - Critical Role of the Descriptor
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Finding Density Functionals with Machine Learning
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Unified Representation of Molecules and Crystals for Machine Learning
• One-shot calculation of temperature-dependent optical spectra and phonon-induced band-gap renormalization
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Lattice dynamics and electron-phonon coupling calculations using non-diagonal supercells
• Temperature Dependence of the Band Gap of Semiconducting Carbon Nanotubes
• Electron-Phonon Coupling from $\text{Ab Initio}$ Linear-Response Theory within the $GW$ Method: Correlation-Enhanced Interactions and Superconductivity in Ba${}_{1-x}$K${}_x$BiO${}_3$
• The temperature dependence of electronic eigenenergies in the adiabatic harmonic approximation
• Machine learning and density functional theory
• Stochastic approach to phonon-assisted optical absorption
• First-principles dynamics of electrons and phonons
• The refractive index and electronic gap of water and ice increase with increasing pressure
• Towards a Predictive First-Principles Description of Solid Molecular Hydrogen with Density-Functional Theory
• Electron-Phonon Coupling and the Metalization of Solid Helium at Terapascal Pressures
• Correlation effects on electron-phonon coupling in semiconductors: many-body theory along thermal lines
• Vibrational averages along thermal lines
• A path-integral molecular dynamics simulation of diamond
• Electron-electron and electron-phonon correlation effects on the finite temperature electronic and optical properties of zb-GaN
• Giant electron-phonon interactions in molecular crystals and the importance of non-quadratic coupling
• Fully Anharmonic, Non-Perturbative Theory of Vibronically Renormalized Electronic Band Structures
• Efficient lattice dynamics calculations for correlated materials with DFT+DMFT
• Machine learning for molecular dynamics with strongly correlated electrons
• Arrested phase separation in double-exchange models: machine-learning enabled large-scale simulation
• Machine learning electron correlation in a disordered medium
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Anomalous phase separation dynamics in a correlated electron system: machine-learning enabled large-scale kinetic Monte Carlo simulations
• Machine learning for phase ordering dynamics of charge density waves
• Machine learning predictions for local electronic properties of disordered correlated electron systems
• Machine learning for structure-property relationships: Scalability and limitations