Analysis of Kohn-Sham Eigenfunctions Using a Convolutional Neural Network in Simulations of the Metal-insulator Transition in Doped Semiconductors

Abstract

Machine learning has recently been applied to many problems in condensed matter physics. A common point of many proposals is to save computational cost by training the machine with data from a simple example and then using the machine to make predictions for a more complicated example. Convolutional neural networks (CNN), which are one of the tools of machine learning, have proved to work well for assessing eigenfunctions in disordered systems. Here we apply a CNN to assess Kohn-Sham eigenfunctions obtained in density functional theory (DFT) simulations of the metal-insulator transition of a doped semiconductor. We demonstrate that a CNN that has been trained using eigenfunctions from a simulation of a doped semiconductor that neglects electron spin successfully predicts the critical concentration when presented with eigenfunctions from simulations that include spin.

arXiv comment7pages, 7 figures

References in corpus (30)

• Machine learning and the physical sciences
• Machine learning phases of matter
• The Kernel Polynomial Method
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learning phase transitions by confusion
• Machine learning a general purpose interatomic potential for silicon
• Machine learning quantum phases of matter beyond the fermion sign problem
• Quantum Loop Topography for Machine Learning
• Multifractal finite-size-scaling and universality at the Anderson transition
• Machine-learning interatomic potential for radiation damage and defects in tungsten
• Critical parameters from generalised multifractal analysis at the Anderson transition
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Phase diagram of disordered higher-order topological insulator: A machine learning study
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Conceptual and practical bases for the high accuracy of machine learning interatomic potential
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Bayesian optimization of chemical composition: a comprehensive framework and its application to $R$Fe${}_{12}$-type magnet compounds
• Finite-size scaling and multifractality at the Anderson transition for the three Wigner-Dyson symmetry classes in three dimensions
• Phase Diagrams of Three-Dimensional Anderson and Quantum Percolation Models using Deep Three-Dimensional Convolutional Neural Network
• Multifractal finite-size scaling at the Anderson transition in the unitary symmetry class
• Critical exponent of metal-insulator transition in doped semiconductors: the relevance of the Coulomb interaction
• Application of Convolutional Neural Network to Quantum Percolation in Topological Insulators
• Data Assimilation Method for Experimental and First-Principles Data: Finite-Temperature Magnetization of (Nd,Pr,La,Ce)${}_2$(Fe,Co,Ni)${}_{14}$B
• Resolution of the exponent puzzle for the Anderson transition in doped semiconductors
• Effect of electron-electron interaction near the metal-insulator transition in doped semiconductors studied within the local density approximation
• Quantum percolation transition in 3d: density of states, finite size scaling and multifractality
• Multifractality of ab initio wave functions in doped semiconductors