EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scalar machine learning of tensorial quantities—Born effective charges from monopole models

Bernhard Schmiedmayer iD, Angela Rittsteuer iD, Tobias Hilpert iD, Georg Kresse iD

The Journal of Chemical Physics · 28.06.2026 · 164 (24)

DOI: 10.1063/5.0327083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 23.06.2026. Verfasst von Bernhard Schmiedmayer und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Physics and Center for Computational Materials Science, University of Vienna, Kolingasse 14-16, A-1090 Vienna, Austria. Die Arbeit nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Austrian Science Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting tensorial properties with machine learning models typically requires carefully designed tensorial descriptors. In this work, we introduce an alternative strategy for learning tensorial quantities based on scalar descriptors. We apply this approach to the Born effective charge tensor, showing that scalar (monopole) kernel models can successfully capture its tensorial nature by exploiting the definition of the Born effective charge tensor as the derivative of the polarization with respect to atomic displacements. We compare this method with tensorial (dipole) kernel models, as established in our previous work, in which the tensorial structure of the Born effective charge is encoded directly in the kernel and obtained via its derivative. Both approaches are then used for charge partitioning, enabling the separation of monopole and dipole contributions. Finally, we demonstrate the effectiveness of the framework by computing finite-temperature infrared spectra for a range of complex materials.

Autor:innen und Institutionen

  • Faculty of Physics and Center for Computational Materials Science, University of Vienna, Kolingasse 14-16, A-1090 Vienna, Austria.
  • Vienna Doctoral School in Physics, Kolingasse 14-16, A-1090 Vienna, Austria.
  • VASP Software GmbH, Berggasse 21/14, A-1090 Vienna, Austria.

ORCID-Profile: Bernhard Schmiedmayer, Angela Rittsteuer, Tobias Hilpert, Georg Kresse

Förderung

  • Austrian Science Fund

Zitieren

APA

Schmiedmayer, B., Rittsteuer, A., Hilpert, T., & Kresse, G. (2026). Scalar machine learning of tensorial quantities—Born effective charges from monopole models. The Journal of Chemical Physics, 164(24). https://doi.org/10.1063/5.0327083

Vancouver

Schmiedmayer B, Rittsteuer A, Hilpert T, Kresse G. Scalar machine learning of tensorial quantities—Born effective charges from monopole models. The Journal of Chemical Physics. 2026;164(24). doi:10.1063/5.0327083

BibTeX
@article{Schmiedmayer2026,
  author = {Schmiedmayer, Bernhard and Rittsteuer, Angela and Hilpert, Tobias and Kresse, Georg},
  title = {Scalar machine learning of tensorial quantities—Born effective charges from monopole models},
  journal = {The Journal of Chemical Physics},
  year = {2026},
  volume = {164},
  number = {24},
  doi = {10.1063/5.0327083}
}
Kostenlos starten →