EUVIMEDEUVIMED entdecken
Open Access

Adapting hybrid density functionals with machine learning

Danish Khan iD, Alastair J A Price iD, Bing Huang, Maximilian L Ach, O Anatole von Lilienfeld iD

Science Advances · 31.01.2025 · 11 (5)

DOI: 10.1126/sciadv.adt7769 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 31.01.2025. Verfasst von Danish Khan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Chemical Physics Theory Group, Department of Chemistry, University of Toronto, St. George Campus, Toronto, ON, Canada. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 159 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exact exchange contributions significantly affect electronic states, influencing covalent bond formation and breaking. Hybrid density functional approximations, which average exact exchange admixtures empirically, have achieved success but fall short of high-level quantum chemistry accuracy due to delocalization errors. We propose adaptive hybrid functionals, generating optimal exact exchange admixture ratios on the fly using data-efficient quantum machine learning models with negligible overhead. The adaptive Perdew-Burke-Ernzerhof hybrid density functional (aPBE0) improves energetics, electron densities, and HOMO-LUMO gaps in QM9, QM7b, and GMTKN55 benchmark datasets. A model uncertainty-based constraint reduces the method smoothly to PBE0 in extrapolative regimes, ensuring general applicability with limited training. By tuning exact exchange fractions for different spin states, aPBE0 effectively addresses the spin gap problem in open-shell systems such as carbenes. We also present a revised QM9 (revQM9) dataset with more accurate quantum properties, including stronger covalent binding, larger bandgaps, more localized electron densities, and larger dipole moments.

Autor:innen und Institutionen

  • Chemical Physics Theory Group, Department of Chemistry, University of Toronto, St. George Campus, Toronto, ON, Canada.
  • Vector Institute for Artificial Intelligence, Toronto, ON, Canada.
  • Acceleration Consortium, University of Toronto, Toronto, ON, Canada.
  • Wuhan University, Department of Chemistry and Molecular Sciences, Wuhan 430072, China.
  • Department of Physics, University of Toronto, St. George Campus, Toronto, ON, Canada.
  • Department of Physics, Ludwig-Maximilians-Universität München (LMU), Munich, Germany.

ORCID-Profile: Danish Khan, Alastair J A Price, O Anatole von Lilienfeld

Zitieren

APA

Khan, D., Price, A. J. A., Huang, B., Ach, M. L., & von Lilienfeld, O. A. (2025). Adapting hybrid density functionals with machine learning. Science Advances, 11(5). https://doi.org/10.1126/sciadv.adt7769

Vancouver

Khan D, Price AJA, Huang B, Ach ML, von Lilienfeld OA. Adapting hybrid density functionals with machine learning. Science Advances. 2025;11(5). doi:10.1126/sciadv.adt7769

BibTeX
@article{Khan2025,
  author = {Khan, Danish and Price, Alastair J A and Huang, Bing and Ach, Maximilian L and von Lilienfeld, O Anatole},
  title = {Adapting hybrid density functionals with machine learning},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {5},
  doi = {10.1126/sciadv.adt7769}
}
Kostenlos starten →