Machine learning density functionals from the random-phase approximation

Abstract

Kohn-Sham density functional theory (DFT) is the standard method for first-principles calculations in computational chemistry and materials science. More accurate theories such as the random-phase approximation (RPA) are limited in application due to their large computational cost. Here, we construct a DFT substitute functional for the RPA using supervised and unsupervised machine learning (ML) techniques. Our ML-RPA model can be interpreted as a non-local extension to the standard gradient approximation. We train an ML-RPA functional for diamond surfaces and liquid water and show that ML-RPA can outperform the standard gradient functionals in terms of accuracy. Our work demonstrates how ML-RPA can extend the applicability of the RPA to larger system sizes, time scales and chemical spaces.

References in corpus (31)

• Van der Waals Density Functional for General Geometries
• On representing chemical environments
• Perspective on density functional theory
• Efficient implementation of a van der Waals density functional: Application to double-wall carbon nanotubes
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Perspective: Advances and challenges in treating van der Waals dispersion forces in density functional theory
• van der Waals forces in density functional theory: The vdW-DF method
• Perspective: How good is DFT for water?
• By-passing the Kohn-Sham equations with machine learning
• On-the-fly machine learning force field generation: Application to melting points
• Finding Density Functionals with Machine Learning
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• Random-phase approximation and its applications in computational chemistry and materials science
• How van der Waals interactions determine the unique properties of water
• Ab initio theory and modeling of water
• On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice
• A Transferable Machine-Learning Model of the Electron Density
• Properties of real metallic surfaces: Effects of density functional semilocality and van der Waals nonlocality
• Incorporating long-range physics in atomic-scale machine learning
• On the physisorption of water on graphene: Sub-chemical accuracy from many-body electronic structure methods
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Structural, Electronic, and Dynamical Properties of Liquid Water by ab initio Molecular Dynamics based on SCAN Functional within the Canonical Ensemble
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• Analytic Interatomic Forces in the Random Phase Approximation
• Electron-Phonon Interactions Using the PAW Method and Wannier Functions
• The random phase approximation applied to ice
• Optimized effective potentials from the random-phase approximation: Accuracy of the quasiparticle approximation
• Plane wave basis set correction methods for RPA correlation energies

Cited by in corpus (5)

• Nonlocal Machine-Learned Exchange Functional for Molecules and Solids
• Addressing the Band Gap Problem with a Machine-Learned Exchange Functional
• Machine learning for accuracy in density functional approximations
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• Quantum-Enhanced Neural Exchange-Correlation Functionals