Predicting electronic screening for fast Koopmans spectral functional calculations

Abstract

Koopmans spectral functionals are a powerful extension of Kohn-Sham density-functional theory (DFT) that enable the prediction of spectral properties with state-of-the-art accuracy. The success of these functionals relies on capturing the effects of electronic screening through scalar, orbital-dependent parameters. These parameters have to be computed for every calculation, making Koopmans spectral functionals more expensive than their DFT counterparts. In this work, we present a machine-learning model that -- with minimal training -- can predict these screening parameters directly from orbital densities calculated at the DFT level. We show on two prototypical use cases that using the screening parameters predicted by this model, instead of those calculated from linear response, leads to orbital energies that differ by less than 20 meV on average. Since this approach dramatically reduces run-times with minimal loss of accuracy, it will enable the application of Koopmans spectral functionals to classes of problems that previously would have been prohibitively expensive, such as the prediction of temperature-dependent spectral properties. More broadly, this work demonstrates that measuring violations of piecewise linearity (i.e. curvature in total energies with respect to occupancies) can be done efficiently by combining frozen-orbital approximations and machine learning.

15 pages with 5 additional pages of Supplementary Information

References in corpus (44)

• 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
• A linear response approach to the calculation of the effective interaction parameters in the LDA+U method
• Optimized norm-conserving Vanderbilt pseudopotentials
• Maximally localized Wannier functions: Theory and applications
• On representing chemical environments
• Machine learning and the physical sciences
• The PseudoDojo: Training and grading a 85 element optimized norm-conserving pseudopotential table
• Nonlocal van der Waals density functional: The simpler the better
• Machine learning for molecular simulation
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• By-passing the Kohn-Sham equations with machine learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Fundamental gaps of finite systems from the eigenvalues of a generalized Kohn-Sham method
• Koopmans' condition for density-functional theory
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Extended DFT+U+V method with on-site and inter-site electronic interactions
• A critical assessment of the Self-Interaction Corrected Local Density Functional method and its algorithmic implementation
• Localized Orbital Scaling Correction for Systematic Elimination of Delocalization Error in Density Functional Approximations
• Deep Learning and Density Functional Theory
• Theory of the special displacement method for electronic structure calculations at finite temperature
• Pressure and stress tensor of complex anharmonic crystals within the stochastic self-consistent harmonic approximation
• Band gaps of crystalline solids from Wannier-localization based optimal tuning of a screened range-separated hybrid functional
• Koopmans-compliant functionals and their performance against reference molecular data
• Recovering the flat-plane condition in electronic structure theory at semi-local DFT cost
• Time-Dependent Self Consistent Harmonic Approximation: Anharmonic nuclear quantum dynamics and time correlation functions
• Ensemble Density Functional Theory of Neutral and Charged Excitations
• Koopmans-compliant functionals and potentials and their application to the GW100 test-set
• Donor and acceptor levels of organic photovoltaic compounds from first principles
• Self-interaction correction with Wannier functions
• First-principles thermodynamics of CsSnI3
• Koopmans Meets Bethe-Salpeter: Excitonic Optical Spectra without GW
• koopmans: an open-source package for accurately and efficiently predicting spectral properties with Koopmans functionals
• Predicting structure-dependent Hubbard U parameters for assessing hybrid functional-level exchange via machine learning
• Bloch's theorem in orbital-density-dependent functionals: Band structures from Koopmans spectral functionals
• Screening in orbital-density-dependent functionals
• Localized orbital scaling correction for periodic systems
• A DFT+U type functional derived to explicitly address the flat plane condition
• Screened extended Koopmans' theorem: photoemission at weak and strong correlation
• Electronic structure of water from Koopmans-compliant functionals
• Testing Koopmans spectral functionals on the analytically-solvable Hooke's atom
• Spin-dependent interactions in orbital-density-dependent functionals: non-collinear Koopmans spectral functionals