Delta Machine Learning for Predicting Dielectric Properties and Raman Spectra

Raman spectroscopy is an important characterization tool with diverse applications in many areas of research. We propose a machine learning (ML) method for predicting polarizabilities with the goal of providing Raman spectra from molecular dynamics trajectories at a reduced computational cost. A linear-response model is used as a first step, and symmetry-adapted ML 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 the training-set sizes required for accurate dielectric properties and Raman spectra in comparison to a single-step ML approach.