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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hawthorne, Felipe, Raulino, Paulo R. E., Pelá, Ronaldo Rodrigues, Woellner, Cristiano F.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908369184358400
author Hawthorne, Felipe
Raulino, Paulo R. E.
Pelá, Ronaldo Rodrigues
Woellner, Cristiano F.
author_facet Hawthorne, Felipe
Raulino, Paulo R. E.
Pelá, Ronaldo Rodrigues
Woellner, Cristiano F.
contents 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 \textit{ab initio} methods. In this work, we present a reactive MLIP for graphene, trained on an extensive dataset generated via \textit{ab initio} molecular dynamics (AIMD) simulations. The model accurately reproduces key mechanical and vibrational properties, including stress-strain behavior, elastic constants, phonon dispersion, and 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 DFT benchmarks. Our MLIP scales linearly with system size, enabling simulations of large graphene sheets with \textit{ab initio}-level precision. This work delivers a robust and transferable MLIP, alongside an accessible training workflow that can be extended to other materials.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient and Accurate Machine Learning Interatomic Potential for Graphene: Capturing Stress-Strain and Vibrational Properties
Hawthorne, Felipe
Raulino, Paulo R. E.
Pelá, Ronaldo Rodrigues
Woellner, Cristiano F.
Materials Science
Computational Physics
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 \textit{ab initio} methods. In this work, we present a reactive MLIP for graphene, trained on an extensive dataset generated via \textit{ab initio} molecular dynamics (AIMD) simulations. The model accurately reproduces key mechanical and vibrational properties, including stress-strain behavior, elastic constants, phonon dispersion, and 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 DFT benchmarks. Our MLIP scales linearly with system size, enabling simulations of large graphene sheets with \textit{ab initio}-level precision. This work delivers a robust and transferable MLIP, alongside an accessible training workflow that can be extended to other materials.
title Efficient and Accurate Machine Learning Interatomic Potential for Graphene: Capturing Stress-Strain and Vibrational Properties
topic Materials Science
Computational Physics
url https://arxiv.org/abs/2505.12140