EUVIMEDEUVIMED entdecken
Crossref

SchrödingerNet: A Universal Neural Network Solver for the Schrödinger Equation

Yaolong Zhang iD, Bin Jiang iD, Hua Guo iD

Journal of Chemical Theory and Computation · 28.01.2025 · 21 (2) · 670-677

DOI: 10.1021/acs.jctc.4c01287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 07.01.2025. Verfasst von Yaolong Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Chemical Biology, Center for Computational Chemistry, University of New Mexico, Albuquerque, New Mexico 87131, United Sta…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Basic Energy Sciences, National Natural Science Foundation of China, Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in machine learning have facilitated numerically accurate solution of the electronic Schrödinger equation (SE) by integrating various neural network (NN)-based wave function ansatzes with variational Monte Carlo methods. Nevertheless, such NN-based methods are all based on the Born-Oppenheimer approximation (BOA) and require computationally expensive training for each nuclear configuration. In this work, we propose a novel NN architecture, SchrödingerNet, to solve the full electronic-nuclear SE by defining a loss function designed to equalize local energies across the system. This approach is based on a translationally, rotationally and permutationally symmetry-adapted total wave function ansatz that includes both nuclear and electronic coordinates. This strategy not only allows for an efficient and accurate generation of a continuous potential energy surface at any geometry within the well-sampled nuclear configuration space, but also incorporates non-BOA corrections, through a single training process. Comparison with benchmarks of atomic and small molecular systems demonstrates its accuracy and efficiency.

Autor:innen und Institutionen

  • Department of Chemistry and Chemical Biology, Center for Computational Chemistry, University of New Mexico, Albuquerque, New Mexico 87131, United States.
  • Key Laboratory of Precision and Intelligent Chemistry, Department of Chemical Physics, University of Science and Technology of China, Hefei, Anhui 230026, China.

ORCID-Profile: Yaolong Zhang, Bin Jiang, Hua Guo

Förderung

  • Basic Energy Sciences
  • National Natural Science Foundation of China
  • Chinese Academy of Sciences

Zitieren

APA

Zhang, Y., Jiang, B., & Guo, H. (2025). SchrödingerNet: A Universal Neural Network Solver for the Schrödinger Equation. Journal of Chemical Theory and Computation, 21(2), 670-677. https://doi.org/10.1021/acs.jctc.4c01287

Vancouver

Zhang Y, Jiang B, Guo H. SchrödingerNet: A Universal Neural Network Solver for the Schrödinger Equation. Journal of Chemical Theory and Computation. 2025;21(2):670-677. doi:10.1021/acs.jctc.4c01287

BibTeX
@article{Zhang2025,
  author = {Zhang, Yaolong and Jiang, Bin and Guo, Hua},
  title = {SchrödingerNet: A Universal Neural Network Solver for the Schrödinger Equation},
  journal = {Journal of Chemical Theory and Computation},
  year = {2025},
  volume = {21},
  number = {2},
  pages = {670--677},
  doi = {10.1021/acs.jctc.4c01287}
}
Kostenlos starten →