Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks

Abstract

We present a numerical modeling workflow based on machine learning (ML) which reproduces the the total energies produced by Kohn-Sham density functional theory (DFT) at finite electronic temperature to within chemical accuracy at negligible computational cost. Based on deep neural networks, our workflow yields the local density of states (LDOS) for a given atomic configuration. From the LDOS, spatially-resolved, energy-resolved, and integrated quantities can be calculated, including the DFT total free energy, which serves as the Born-Oppenheimer potential energy surface for the atoms. We demonstrate the efficacy of this approach for both solid and liquid metals and compare results between independent and unified machine-learning models for solid and liquid aluminum. Our machine-learning density functional theory framework opens up the path towards multiscale materials modeling for matter under ambient and extreme conditions at a computational scale and cost that is unattainable with current algorithms.

References in corpus (13)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Restoring the density-gradient expansion for exchange in solids and surfaces
• Generalized gradient approximation for solids and their surfaces
• Advanced capabilities for materials modelling with Quantum ESPRESSO
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum ESPRESSO toward the exascale
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Massive Core in Jupiter Predicted From First-Principles Simulations
• Hydrogen-Helium Mixtures in the Interiors of Giant Planets
• DFT: A Theory Full of Holes?
• Learning the electronic density of states in condensed matter
• Data-driven Material Models for Atomistic Simulation
• Ab Initio Molecular Dynamics on the Electronic Boltzmann Equilibrium Distribution

Cited by in corpus (24)

• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Electronic Density Response of Warm Dense Matter
• First principles simulations of dense hydrogen
• Predicting electronic structures at any length scale with machine learning
• Robustness of Local Predictions in Atomistic Machine Learning Models
• Accelerating Equilibration in First-Principles Molecular Dynamics with Orbital-Free Density Functional Theory
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Towards a Quantum Fluid Theory of Correlated Many-Fermion Systems from First Principles
• Grad DFT: a software library for machine learning enhanced density functional theory
• First-principles derivation and properties of density-functional average-atom models
• Towards Large-Scale and Spatio-temporally Resolved Diagnosis of Electronic Density of States by Deep Learning
• Predicting The One-Particle Density Matrix With Machine Learning
• Predicting hot-electron free energies from ground-state data
• Training-free hyperparameter optimization of neural networks for electronic structures in matter
• Machine learning the electronic structure of matter across temperatures
• Equivariant Tensor Network Potentials
• Electronic specific heat capacities and entropies from density matrix quantum Monte Carlo using Gaussian process regression to find gradients of noisy data
• Piecewise Interaction Picture Density Matrix Quantum Monte Carlo
• Effect of molecular and electronic geometries on the electronic density in FLO-SIC
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Physics-enhanced neural networks for equation-of-state calculations
• atoMEC: An open-source average-atom Python code
• Machine learning based prediction of the electronic structure of quasi-one-dimensional materials under strain
• A charge-density machine-learning workflow for computing the infrared spectrum of molecules