EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Δ-learning strategy for interpretation of spectroscopic observables

Luke Watson iD, Thomas Pope iD, Raphael M Jay iD, Ambar Banerjee iD, Philippe Wernet iD, Thomas J Penfold iD

Structural Dynamics · 01.11.2023 · 10 (6)

DOI: 10.1063/4.0000215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structural Dynamics, online erschienen am 06.11.2023. Verfasst von Luke Watson und 5 weiteren Autor:innen. Beteiligte Einrichtung: Chemistry, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate computations of experimental observables are essential for interpreting the high information content held within x-ray spectra. However, for complicated systems this can be difficult, a challenge compounded when dynamics becomes important owing to the large number of calculations required to capture the time-evolving observable. While machine learning architectures have been shown to represent a promising approach for rapidly predicting spectral lineshapes, achieving simultaneously accurate and sufficiently comprehensive training data is challenging. Herein, we introduce Δ-learning for x-ray spectroscopy. Instead of directly learning the structure-spectrum relationship, the Δ-model learns the structure dependent difference between a higher and lower level of theory. Consequently, once developed these models can be used to translate spectral shapes obtained from lower levels of theory to mimic those corresponding to higher levels of theory. Ultimately, this achieves accurate simulations with a much reduced computational burden as only the lower level of theory is computed, while the model can instantaneously transform this to a spectrum equivalent to a higher level of theory. Our present model, demonstrated herein, learns the difference between TDDFT(BLYP) and TDDFT(B3LYP) spectra. Its effectiveness is illustrated using simulations of Rh L3-edge spectra tracking the C–H activation of octane by a cyclopentadienyl rhodium carbonyl complex.

Autor:innen und Institutionen

  • Chemistry, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom.
  • Department of Physics and Astronomy, Uppsala University, 751 20 Uppsala, Sweden.

ORCID-Profile: Luke Watson, Thomas Pope, Raphael M Jay, Ambar Banerjee, Philippe Wernet, Thomas J Penfold

Zitieren

APA

Watson, L., Pope, T., Jay, R. M., Banerjee, A., Wernet, P., & Penfold, T. J. (2023). A Δ-learning strategy for interpretation of spectroscopic observables. Structural Dynamics, 10(6). https://doi.org/10.1063/4.0000215

Vancouver

Watson L, Pope T, Jay RM, Banerjee A, Wernet P, Penfold TJ. A Δ-learning strategy for interpretation of spectroscopic observables. Structural Dynamics. 2023;10(6). doi:10.1063/4.0000215

BibTeX
@article{Watson2023,
  author = {Watson, Luke and Pope, Thomas and Jay, Raphael M and Banerjee, Ambar and Wernet, Philippe and Penfold, Thomas J},
  title = {A Δ-learning strategy for interpretation of spectroscopic observables},
  journal = {Structural Dynamics},
  year = {2023},
  volume = {10},
  number = {6},
  doi = {10.1063/4.0000215}
}
Kostenlos starten →