EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials

Zheyong Fan, Wenjun Zhang, Zhenhao Zhang, Ke Xu, Xuecheng Shao, Haikuan Dong

Computational Materials Today · 2026-06 · 10 · 100055

DOI: 10.1016/j.commt.2026.100055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Materials Today, 2026-06. Verfasst von Zheyong Fan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Department of Education of Liaoning Province, Department of Science and Technology of Liaoning Province, National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine-learned coarse-grained (CG) models often suffer from noisy training data, limiting their accuracy and transferability. We propose a method to generate low-noise training data based on the potential of mean force by constraining CG beads during atomistic simulations and accumulating time-averaged forces. Implemented within the neuroevolution potential (NEP) framework, our approach achieves training accuracy comparable to atomistic models trained on density functional theory data. For liquid water, the NEP-CG model accurately reproduces densities from 1 bar to 1 GPa, successfully extrapolating beyond the 0.5 GPa training limit, with a virial correction essential for the correct equation of state. For an anisotropic C$_{60}$ monolayer, distinguishing crystallographically distinct bead types reduces stress errors by an order of magnitude and captures directional thermal conductivity. We further introduce a multiscale NEP-AACG model integrating all-atom (AA) and CG degrees of freedom, demonstrated for gold nanowire fracture at an experimentally relevant strain rate. Computational speeds for NEP-CG models reach hundreds to thousands of ns/day using a single consumer-grade GPU. This work provides a robust framework for constructing accurate, transferable, and efficient CG models across diverse systems.

Förderung

  • Department of Education of Liaoning Province
  • Department of Science and Technology of Liaoning Province
  • National Science and Technology Major Project

Zitieren

APA

Fan, Z., Zhang, W., Zhang, Z., Xu, K., Shao, X., & Dong, H. (2026). NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials. Computational Materials Today, 10, 100055. https://doi.org/10.1016/j.commt.2026.100055

Vancouver

Fan Z, Zhang W, Zhang Z, Xu K, Shao X, Dong H. NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials. Computational Materials Today. 2026;10:100055. doi:10.1016/j.commt.2026.100055

BibTeX
@article{Fan2026,
  author = {Fan, Zheyong and Zhang, Wenjun and Zhang, Zhenhao and Xu, Ke and Shao, Xuecheng and Dong, Haikuan},
  title = {NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials},
  journal = {Computational Materials Today},
  year = {2026},
  volume = {10},
  pages = {100055},
  doi = {10.1016/j.commt.2026.100055}
}
Kostenlos starten →