TY - JOUR
T1 - Deep learning model to predict fracture mechanisms of graphene
AU - Lew, Andrew J.
AU - Yu, Chi Hua
AU - Hsu, Yu Chuan
AU - Buehler, Markus J.
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Understanding fracture is critical to the design of resilient nanomaterials. Molecular dynamics offers a way to study fracture at an atomistic level, but is computationally expensive with limitations of scalability. In this work, we build upon machine-learning approaches for predicting nanoscopic fracture mechanisms including crack instabilities and branching as a function of crystal orientation. We focus on a particular technologically relevant material system, graphene, and apply a deep learning method to the study of such nanomaterials and explore the parameter space necessary for calibrating machine-learning predictions to meaningful results. Our results validate the ability of deep learning methods to quantitatively capture graphene fracture behavior, including its fractal dimension as a function of crystal orientation, and provide promise toward the wider application of deep learning to materials design, opening the potential for other 2D materials.
AB - Understanding fracture is critical to the design of resilient nanomaterials. Molecular dynamics offers a way to study fracture at an atomistic level, but is computationally expensive with limitations of scalability. In this work, we build upon machine-learning approaches for predicting nanoscopic fracture mechanisms including crack instabilities and branching as a function of crystal orientation. We focus on a particular technologically relevant material system, graphene, and apply a deep learning method to the study of such nanomaterials and explore the parameter space necessary for calibrating machine-learning predictions to meaningful results. Our results validate the ability of deep learning methods to quantitatively capture graphene fracture behavior, including its fractal dimension as a function of crystal orientation, and provide promise toward the wider application of deep learning to materials design, opening the potential for other 2D materials.
UR - http://www.scopus.com/inward/record.url?scp=85105167886&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105167886&partnerID=8YFLogxK
U2 - 10.1038/s41699-021-00228-x
DO - 10.1038/s41699-021-00228-x
M3 - Article
AN - SCOPUS:85105167886
SN - 2397-7132
VL - 5
JO - npj 2D Materials and Applications
JF - npj 2D Materials and Applications
IS - 1
M1 - 48
ER -