skip to main content
Idioma:

Physically inspired deep learning of molecular excitations and photoemission spectra

Westermayr, Julia ; Maurer, Reinhard J

Chemical science (Cambridge), 2021-08, Vol.12 (32), p.1755-1764 [Periódico revisado por pares]

Cambridge: Royal Society of Chemistry

Texto completo disponível

Citações Citado por
  • Título:
    Physically inspired deep learning of molecular excitations and photoemission spectra
  • Autor: Westermayr, Julia ; Maurer, Reinhard J
  • Assuntos: Artificial neural networks ; Chemical composition ; Chemistry ; Complexity ; Eigenvalues ; Elementary excitations ; Excitation ; Excitation spectra ; First principles ; Functional materials ; Machine learning ; Optoelectronics ; Organic chemistry ; Perturbation theory ; Photoelectric emission
  • É parte de: Chemical science (Cambridge), 2021-08, Vol.12 (32), p.1755-1764
  • Notas: Electronic supplementary information (ESI) available. See DOI
    10.1039/d1sc01542g
    ObjectType-Article-1
    SourceType-Scholarly Journals-1
    ObjectType-Feature-2
    content type line 23
  • Descrição: 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. A physically-inspired machine learning model for orbital energies is developed that can be augmented with delta learning to obtain photoemission spectra, ionization potentials, and electron affinities with experimental accuracy.
  • Editor: Cambridge: Royal Society of Chemistry
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.