Delta Machine Learning for Predicting Dielectric Properties and Raman Spectra

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grumet, Manuel, von Scarpatetti, Clara, Bučko, Tomáš, Egger, David A.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914663066763264
author Grumet, Manuel
von Scarpatetti, Clara
Bučko, Tomáš
Egger, David A.
author_facet Grumet, Manuel
von Scarpatetti, Clara
Bučko, Tomáš
Egger, David A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_10578
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Delta Machine Learning for Predicting Dielectric Properties and Raman Spectra
Grumet, Manuel
von Scarpatetti, Clara
Bučko, Tomáš
Egger, David A.
Materials Science
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.
title Delta Machine Learning for Predicting Dielectric Properties and Raman Spectra
topic Materials Science
url https://arxiv.org/abs/2307.10578