Delta Machine Learning for Predicting Dielectric Properties and Raman Spectra

TL;DR

This paper introduces a delta machine learning approach combining linear-response models and symmetry-adapted methods to efficiently predict dielectric properties and Raman spectra from molecular dynamics data, reducing computational costs.

Contribution

It presents a novel two-step delta machine learning framework that improves prediction accuracy and reduces training data requirements for dielectric and Raman spectral properties.

Findings

Effective in molecules and solids

Reduces training set size needed

Maintains high prediction accuracy

Abstract

Raman spectroscopy is an important characterization tool with diverse applications in many areas of research. We propose a machine learning method for predicting polarizabilities with the goal of providing Raman spectra from molecular dynamics trajectories at reduced computational cost. A linear-response model is used as a first step and symmetry-adapted machine learning is employed for the higher-order contributions as a second step. We investigate the performance of the approach for several systems including molecules and extended solids. The method can reduce training set sizes required for accurate dielectric properties and Raman spectra in comparison to a single-step machine learning approach.