Efficient and Accurate Machine Learning Interatomic Potential for Graphene: Capturing Stress-Strain and Vibrational Properties

F Hawthorne and PRE Raulino and RR Pelá and CF Woellner, JOURNAL OF PHYSICAL CHEMISTRY C, 129, 16319-16326 (2025).

DOI: 10.1021/acs.jpcc.5c03470

Machine learning interatomic potentials (MLIPs) offer an efficient and accurate framework for large-scale molecular dynamics (MD) simulations, effectively bridging the gap between classical force fields and ab initio methods. In this work, we present a reactive MLIP for graphene, trained on an extensive data set generated via ab initio molecular dynamics (AIMD) simulations performed using the local density approximation (LDA) exchange-correlation functional and the projector- augmented wave (PAW) method. The model accurately reproduces key mechanical and vibrational properties, including stress-strain behavior, elastic constants, phonon dispersion, and the vibrational density of states. Notably, it captures temperature-dependent fracture mechanisms and the emergence of linear acetylenic carbon chains upon tearing. The phonon analysis also reveals the expected quadratic ZA mode and excellent agreement with experimental and density functional theory (DFT) benchmarks. Our MLIP scales linearly with system size, enabling simulations of large graphene sheets with ab initio-level precision. This work delivers a robust and transferable MLIP, alongside an accessible training workflow that can be extended to other materials.

Return to Publications page