Hybrid neural network potential for multilayer graphene

Mingjian Wen, Ellad B. Tadmor

Research output: Contribution to journalArticlepeer-review

43 Scopus citations


Monolayer and multilayer graphene are promising materials for applications such as electronic devices, sensors, energy generation and storage, and medicine. In order to perform large-scale atomistic simulations of the mechanical and thermal behavior of graphene-based devices, accurate interatomic potentials are required. Here, we present an interatomic potential for multilayer graphene structures referred to as "hNN-Grx." This hybrid potential employs a neural network to describe short-range interactions and a theoretically motivated analytical term to model long-range dispersion. The potential is trained against a large dataset of monolayer graphene, bilayer graphene, and graphite configurations obtained from ab initio total-energy calculations based on density functional theory (DFT). The potential provides accurate energy and forces for both intralayer and interlayer interactions, correctly reproducing DFT results for structural, energetic, and elastic properties such as the equilibrium layer spacing, interlayer binding energy, elastic moduli, and phonon dispersions to which it was not fit. The potential is used to study the effect of vacancies on thermal conductivity in monolayer graphene and interlayer friction in bilayer graphene. The potential is available through the openkim interatomic potential repository at https://openkim.org.

Original languageEnglish (US)
Article number195419
JournalPhysical Review B
Issue number19
StatePublished - Nov 18 2019

Bibliographical note

Funding Information:
This research was partly supported by the US Army Research Office (Grant No. W911NF-14-1-0247) under the Multidisciplinary University Research Initiative program, by the National Science Foundation under Grants No. DMR-1834251 and No. DMR-1834332, and through the University of Minnesota MRSEC program under Grant No. DMR-1420013. The authors acknowledge the Minnesota Supercomputing Institute at the University of Minnesota for providing resources that contributed to the results reported in this paper. We thank Efthimios Kaxiras and Ryan Elliott for helpful discussion. M.W. acknowledges the University of Minnesota Doctoral Dissertation Fellowship for supporting his research.

MRSEC Support

  • Partial


Dive into the research topics of 'Hybrid neural network potential for multilayer graphene'. Together they form a unique fingerprint.

Cite this