EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fidelity of Machine-Learned Potentials: Quantitative Assessment for Protonated Oxalate

Chen Qu, Paul L. Houston, Qi Yu, Apurba Nandi, Joel M. Bowman, Valerii Andreichev, Silvan Käser, Markus Meuwly

PRX Intelligence · 2026

DOI: 10.1103/jfjx-djk2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PRX Intelligence, 2026. Verfasst von Chen Qu und 7 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Universität Basel, European Cooperation in Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

There has been a veritable explosion of methods and software to perform machine-learned regression on datasets of electronic energies and forces to develop high-dimensional machine-learned potential energy surfaces (ML-PESs). A major, but not deeply studied aspect is how well different ML-PESs represent the same dataset on which they were trained, beyond the standard statistical precision measures. Here, this is examined using several “stress tests,” for two widely used machine-learned potential approaches. One is based on permutationally invariant polynomial linear least-square regression and the other is the message-passing neural network PhysNet approach. The energies from the two PESs are directly compared as are the IR spectra determined from vibrational self-consistent field/vibrational configuration interaction calculations using fitted dipole moment surfaces. In addition, tunneling splittings for the hydrogen transfer between two equivalent structures are reported using three different methods: ring polymer instanton theory, diffusion Monte Carlo simulations, and the Q i m -path method. These calculations require the evaluation of on the order of one billion energies that are widely dispersed in the 15-dimensional configurational space. The two PESs yield results for these quantities in excellent agreement with each other.

Förderung

  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
  • Universität Basel
  • European Cooperation in Science and Technology

Zitieren

APA

Qu, C., Houston, P. L., Yu, Q., Nandi, A., Bowman, J. M., Andreichev, V., Käser, S., & Meuwly, M. (2026). Fidelity of Machine-Learned Potentials: Quantitative Assessment for Protonated Oxalate. PRX Intelligence. https://doi.org/10.1103/jfjx-djk2

Vancouver

Qu C, Houston PL, Yu Q, Nandi A, Bowman JM, Andreichev V, et al. Fidelity of Machine-Learned Potentials: Quantitative Assessment for Protonated Oxalate. PRX Intelligence. 2026. doi:10.1103/jfjx-djk2

BibTeX
@article{Qu2026,
  author = {Qu, Chen and Houston, Paul L. and Yu, Qi and Nandi, Apurba and Bowman, Joel M. and Andreichev, Valerii and Käser, Silvan and Meuwly, Markus},
  title = {Fidelity of Machine-Learned Potentials: Quantitative Assessment for Protonated Oxalate},
  journal = {PRX Intelligence},
  year = {2026},
  doi = {10.1103/jfjx-djk2}
}
Kostenlos starten →