Artificial neural network potentials for mechanics and fracture dynamics of two-dimensional crystals**

Gang Seob Jung; Hunjoo Myung; Stephan Irle

doi:10.1088/2632-2153/accd45

Artificial neural network potentials for mechanics and fracture dynamics of two-dimensional crystals**

Gang Seob Jung, Hunjoo Myung, Stephan Irle

Computational Chemistry and Nanomaterial

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Understanding the mechanics and failure of materials at the nanoscale is critical for their engineering and applications. The accurate atomistic modeling of brittle failure with crack propagation in covalent crystals requires a quantum mechanics-based description of individual bond-breaking events. Artificial neural network potentials (NNPs) have emerged to overcome the traditional, physics-based modeling tradeoff between accuracy and accessible time and length scales. Previous studies have shown successful applications of NNPs for describing the structure and dynamics of molecular systems and amorphous or liquid phases of materials. However, their application to deformation and failure processes in materials is still uncommon. In this study, we discuss the apparent limitations of NNPs for the description of deformation and fracture under loadings and propose a way to generate and select training data for their employment in simulations of deformation and fracture simulations of crystals. We applied the proposed approach to 2D crystalline graphene, utilizing the density-functional tight-binding method for more efficient and extensive data generation in place of density functional theory. Then, we explored how the data selection affects the accuracy of the developed artificial NNPs. It revealed that NNP’s reliability should not only be measured based on the total energy and atomic force comparisons for reference structures but also utilize comparisons for physical properties, e.g. stress-strain curves and geometric deformation. In sharp contrast to popular reactive bond order potentials, our optimized NNP predicts straight crack propagation in graphene along both armchair and zigzag (ZZ) lattice directions, as well as higher fracture toughness of ZZ edge direction. Our study provides significant insight into crack propagation mechanisms on atomic scales and highlights strategies for NNP developments of broader materials.

Original language	English
Article number	035001
Journal	Machine Learning: Science and Technology
Volume	4
Issue number	3
DOIs	https://doi.org/10.1088/2632-2153/accd45
State	Published - Sep 1 2023

Funding

** Notice: This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan ). The authors acknowledge helpful comments and discussion with J Warner. G S J and S I acknowledge support by the U. S. Department of Energy Fossile Energy and Carbon Management Program, Advanced Coal Processing Program, C4WARD project (FWP No. FEAA155). G S J acknowledges support for method developments by the Laboratory Directed Research and Development (LDRD), Eugene P Wigner Fellowship, Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy. S I acknowledges partial support from the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory. This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.

Funders	Funder number
Advanced Coal Processing Program	FEAA155
Artificial Intelligence Initiative
CADES
Data Environment for Science
U. S. Department of Energy Fossile Energy and Carbon Management Program
U.S. Department of Energy	DE-AC05-00OR22725
Office of Science
Oak Ridge National Laboratory
Laboratory Directed Research and Development

Keywords

2D materials
crack propagation
fracture
graphene
mechanics
neural network potential

Access to Document

10.1088/2632-2153/accd45

Cite this

@article{4daf9bd3bafd47f68cdbb8ef4b9d945c,

title = "Artificial neural network potentials for mechanics and fracture dynamics of two-dimensional crystals**",

abstract = "Understanding the mechanics and failure of materials at the nanoscale is critical for their engineering and applications. The accurate atomistic modeling of brittle failure with crack propagation in covalent crystals requires a quantum mechanics-based description of individual bond-breaking events. Artificial neural network potentials (NNPs) have emerged to overcome the traditional, physics-based modeling tradeoff between accuracy and accessible time and length scales. Previous studies have shown successful applications of NNPs for describing the structure and dynamics of molecular systems and amorphous or liquid phases of materials. However, their application to deformation and failure processes in materials is still uncommon. In this study, we discuss the apparent limitations of NNPs for the description of deformation and fracture under loadings and propose a way to generate and select training data for their employment in simulations of deformation and fracture simulations of crystals. We applied the proposed approach to 2D crystalline graphene, utilizing the density-functional tight-binding method for more efficient and extensive data generation in place of density functional theory. Then, we explored how the data selection affects the accuracy of the developed artificial NNPs. It revealed that NNP{\textquoteright}s reliability should not only be measured based on the total energy and atomic force comparisons for reference structures but also utilize comparisons for physical properties, e.g. stress-strain curves and geometric deformation. In sharp contrast to popular reactive bond order potentials, our optimized NNP predicts straight crack propagation in graphene along both armchair and zigzag (ZZ) lattice directions, as well as higher fracture toughness of ZZ edge direction. Our study provides significant insight into crack propagation mechanisms on atomic scales and highlights strategies for NNP developments of broader materials.",

keywords = "2D materials, crack propagation, fracture, graphene, mechanics, neural network potential",

author = "Jung, {Gang Seob} and Hunjoo Myung and Stephan Irle",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s). Published by IOP Publishing Ltd.",

year = "2023",

month = sep,

day = "1",

doi = "10.1088/2632-2153/accd45",

language = "English",

volume = "4",

journal = "Machine Learning: Science and Technology",

issn = "2632-2153",

publisher = "IOP Publishing",

number = "3",

}

TY - JOUR

T1 - Artificial neural network potentials for mechanics and fracture dynamics of two-dimensional crystals**

AU - Jung, Gang Seob

AU - Myung, Hunjoo

AU - Irle, Stephan

PY - 2023/9/1

Y1 - 2023/9/1

N2 - Understanding the mechanics and failure of materials at the nanoscale is critical for their engineering and applications. The accurate atomistic modeling of brittle failure with crack propagation in covalent crystals requires a quantum mechanics-based description of individual bond-breaking events. Artificial neural network potentials (NNPs) have emerged to overcome the traditional, physics-based modeling tradeoff between accuracy and accessible time and length scales. Previous studies have shown successful applications of NNPs for describing the structure and dynamics of molecular systems and amorphous or liquid phases of materials. However, their application to deformation and failure processes in materials is still uncommon. In this study, we discuss the apparent limitations of NNPs for the description of deformation and fracture under loadings and propose a way to generate and select training data for their employment in simulations of deformation and fracture simulations of crystals. We applied the proposed approach to 2D crystalline graphene, utilizing the density-functional tight-binding method for more efficient and extensive data generation in place of density functional theory. Then, we explored how the data selection affects the accuracy of the developed artificial NNPs. It revealed that NNP’s reliability should not only be measured based on the total energy and atomic force comparisons for reference structures but also utilize comparisons for physical properties, e.g. stress-strain curves and geometric deformation. In sharp contrast to popular reactive bond order potentials, our optimized NNP predicts straight crack propagation in graphene along both armchair and zigzag (ZZ) lattice directions, as well as higher fracture toughness of ZZ edge direction. Our study provides significant insight into crack propagation mechanisms on atomic scales and highlights strategies for NNP developments of broader materials.

AB - Understanding the mechanics and failure of materials at the nanoscale is critical for their engineering and applications. The accurate atomistic modeling of brittle failure with crack propagation in covalent crystals requires a quantum mechanics-based description of individual bond-breaking events. Artificial neural network potentials (NNPs) have emerged to overcome the traditional, physics-based modeling tradeoff between accuracy and accessible time and length scales. Previous studies have shown successful applications of NNPs for describing the structure and dynamics of molecular systems and amorphous or liquid phases of materials. However, their application to deformation and failure processes in materials is still uncommon. In this study, we discuss the apparent limitations of NNPs for the description of deformation and fracture under loadings and propose a way to generate and select training data for their employment in simulations of deformation and fracture simulations of crystals. We applied the proposed approach to 2D crystalline graphene, utilizing the density-functional tight-binding method for more efficient and extensive data generation in place of density functional theory. Then, we explored how the data selection affects the accuracy of the developed artificial NNPs. It revealed that NNP’s reliability should not only be measured based on the total energy and atomic force comparisons for reference structures but also utilize comparisons for physical properties, e.g. stress-strain curves and geometric deformation. In sharp contrast to popular reactive bond order potentials, our optimized NNP predicts straight crack propagation in graphene along both armchair and zigzag (ZZ) lattice directions, as well as higher fracture toughness of ZZ edge direction. Our study provides significant insight into crack propagation mechanisms on atomic scales and highlights strategies for NNP developments of broader materials.

KW - 2D materials

KW - crack propagation

KW - fracture

KW - graphene

KW - mechanics

KW - neural network potential

UR - http://www.scopus.com/inward/record.url?scp=85165205520&partnerID=8YFLogxK

U2 - 10.1088/2632-2153/accd45

DO - 10.1088/2632-2153/accd45

M3 - Article

AN - SCOPUS:85165205520

SN - 2632-2153

VL - 4

JO - Machine Learning: Science and Technology

JF - Machine Learning: Science and Technology

IS - 3

M1 - 035001

ER -

Artificial neural network potentials for mechanics and fracture dynamics of two-dimensional crystals**

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this