Cargando…

Physically inspired deep learning of molecular excitations and photoemission spectra

Modern functional materials consist of large molecular building blocks with significant chemical complexity which limits spectroscopic property prediction with accurate first-principles methods. Consequently, a targeted design of materials with tailored optoelectronic properties by high-throughput s...

Descripción completa

Detalles Bibliográficos
Autores principales: Westermayr, Julia, Maurer, Reinhard J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society of Chemistry 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372319/
https://www.ncbi.nlm.nih.gov/pubmed/34447563
http://dx.doi.org/10.1039/d1sc01542g
_version_ 1783739778732130304
author Westermayr, Julia
Maurer, Reinhard J.
author_facet Westermayr, Julia
Maurer, Reinhard J.
author_sort Westermayr, Julia
collection PubMed
description Modern functional materials consist of large molecular building blocks with significant chemical complexity which limits spectroscopic property prediction with accurate first-principles methods. Consequently, a targeted design of materials with tailored optoelectronic properties by high-throughput screening is bound to fail without efficient methods to predict molecular excited-state properties across chemical space. In this work, we present a deep neural network that predicts charged quasiparticle excitations for large and complex organic molecules with a rich elemental diversity and a size well out of reach of accurate many body perturbation theory calculations. The model exploits the fundamental underlying physics of molecular resonances as eigenvalues of a latent Hamiltonian matrix and is thus able to accurately describe multiple resonances simultaneously. The performance of this model is demonstrated for a range of organic molecules across chemical composition space and configuration space. We further showcase the model capabilities by predicting photoemission spectra at the level of the GW approximation for previously unseen conjugated molecules.
format Online
Article
Text
id pubmed-8372319
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher The Royal Society of Chemistry
record_format MEDLINE/PubMed
spelling pubmed-83723192021-08-25 Physically inspired deep learning of molecular excitations and photoemission spectra Westermayr, Julia Maurer, Reinhard J. Chem Sci Chemistry Modern functional materials consist of large molecular building blocks with significant chemical complexity which limits spectroscopic property prediction with accurate first-principles methods. Consequently, a targeted design of materials with tailored optoelectronic properties by high-throughput screening is bound to fail without efficient methods to predict molecular excited-state properties across chemical space. In this work, we present a deep neural network that predicts charged quasiparticle excitations for large and complex organic molecules with a rich elemental diversity and a size well out of reach of accurate many body perturbation theory calculations. The model exploits the fundamental underlying physics of molecular resonances as eigenvalues of a latent Hamiltonian matrix and is thus able to accurately describe multiple resonances simultaneously. The performance of this model is demonstrated for a range of organic molecules across chemical composition space and configuration space. We further showcase the model capabilities by predicting photoemission spectra at the level of the GW approximation for previously unseen conjugated molecules. The Royal Society of Chemistry 2021-06-30 /pmc/articles/PMC8372319/ /pubmed/34447563 http://dx.doi.org/10.1039/d1sc01542g Text en This journal is © The Royal Society of Chemistry https://creativecommons.org/licenses/by/3.0/
spellingShingle Chemistry
Westermayr, Julia
Maurer, Reinhard J.
Physically inspired deep learning of molecular excitations and photoemission spectra
title Physically inspired deep learning of molecular excitations and photoemission spectra
title_full Physically inspired deep learning of molecular excitations and photoemission spectra
title_fullStr Physically inspired deep learning of molecular excitations and photoemission spectra
title_full_unstemmed Physically inspired deep learning of molecular excitations and photoemission spectra
title_short Physically inspired deep learning of molecular excitations and photoemission spectra
title_sort physically inspired deep learning of molecular excitations and photoemission spectra
topic Chemistry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372319/
https://www.ncbi.nlm.nih.gov/pubmed/34447563
http://dx.doi.org/10.1039/d1sc01542g
work_keys_str_mv AT westermayrjulia physicallyinspireddeeplearningofmolecularexcitationsandphotoemissionspectra
AT maurerreinhardj physicallyinspireddeeplearningofmolecularexcitationsandphotoemissionspectra