EUVIMEDEUVIMED entdecken
Crossref

Uncertainty Based Machine Learning-DFT Hybrid Framework for Accelerating Geometry Optimization

Akksay Singh iD, Jiaqi Wang, Graeme Henkelman iD, Lei Li iD

Journal of Chemical Theory and Computation · 26.11.2024 · 20 (22) · 10022-10033

DOI: 10.1021/acs.jctc.4c00953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 12.11.2024. Verfasst von Akksay Singh und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Materials Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Division of Chemistry, Welch Foundation, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Geometry optimization is an important tool used for computational simulations in the fields of chemistry, physics, and material science. Developing more efficient and reliable algorithms to reduce the number of force evaluations would lead to accelerated computational modeling and materials discovery. Here, we present a delta method-based neural network-density functional theory (DFT) hybrid optimizer to improve the computational efficiency of geometry optimization. Compared to previous active learning approaches, our algorithm adds two key features: a modified delta method incorporating force information to enhance efficiency in uncertainty estimation, and a quasi-Newton approach based upon a Hessian matrix calculated from the neural network; the later improving stability of optimization near critical points. We benchmarked our optimizer against commonly used optimization algorithms using systems including bulk metal, metal surface, metal hydride, and an oxide cluster. The results demonstrate that our optimizer effectively reduces the number of DFT force calls by 2-3 times in all test systems.

Autor:innen und Institutionen

  • Department of Materials Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China.
  • Department of Chemistry, The University of Texas at Austin, Austin, Texas 78712, United States.
  • Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas 78712, United States.

ORCID-Profile: Akksay Singh, Graeme Henkelman, Lei Li

Förderung

  • Division of Chemistry
  • Welch Foundation
  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Singh, A., Wang, J., Henkelman, G., & Li, L. (2024). Uncertainty Based Machine Learning-DFT Hybrid Framework for Accelerating Geometry Optimization. Journal of Chemical Theory and Computation, 20(22), 10022-10033. https://doi.org/10.1021/acs.jctc.4c00953

Vancouver

Singh A, Wang J, Henkelman G, Li L. Uncertainty Based Machine Learning-DFT Hybrid Framework for Accelerating Geometry Optimization. Journal of Chemical Theory and Computation. 2024;20(22):10022-10033. doi:10.1021/acs.jctc.4c00953

BibTeX
@article{Singh2024,
  author = {Singh, Akksay and Wang, Jiaqi and Henkelman, Graeme and Li, Lei},
  title = {Uncertainty Based Machine Learning-DFT Hybrid Framework for Accelerating Geometry Optimization},
  journal = {Journal of Chemical Theory and Computation},
  year = {2024},
  volume = {20},
  number = {22},
  pages = {10022--10033},
  doi = {10.1021/acs.jctc.4c00953}
}
Kostenlos starten →