Electronic Response Quantities of Solids and Deep Learning

TL;DR

This paper presents RADNET, a deep learning framework that accurately predicts electronic response properties of solids, enabling efficient calculations of dielectric functions, Born charges, and Raman spectra with ab initio accuracy.

Contribution

RADNET introduces a novel deep neural network approach for predicting electronic response quantities in solids, outperforming existing methods and enabling scalable simulations.

Findings

RADNET achieves high accuracy in predicting dielectric functions and related properties.

It accurately reproduces Raman spectra for GaAs and BN.

RADNET scales effectively to larger systems for response function predictions.

Abstract

We introduce a deep neural network (DNN) framework called the \textbf{r}eal-space \textbf{a}tomic \textbf{d}ecomposition \textbf{net}work (\textsc{radnet}), which is capable of making accurate polarization and static dielectric function predictions for solids. We use these predictions to calculate Born-effective charges, longitudinal optical transverse optical (LO-TO) splitting frequencies, and Raman tensors for two prototypical examples: GaAs and BN. We then compute the Raman spectra, and find excellent agreement with \textit{ab initio} techniques. \textsc{radnet} is as good or better than current methodologies. Lastly, we discuss how \textsc{radnet} scales to larger systems, paving the way for predictions of response functions on meso-scale structures with \textit{ab initio} accuracy.