Predicting electronic screening for fast Koopmans spectral functional calculations

TL;DR

This paper introduces a machine learning approach to predict screening parameters in Koopmans spectral functionals, significantly reducing computational costs while maintaining high accuracy, thus broadening their practical applicability.

Contribution

The work develops a minimal-training machine learning model to predict screening parameters from DFT orbital densities, enabling faster spectral property calculations.

Findings

Predicted screening parameters yield orbital energies within 20 meV of linear response calculations.

The approach reduces computational time dramatically with minimal accuracy loss.

Enables application of Koopmans functionals to temperature-dependent spectral predictions.

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.