TY - JOUR
T1 - Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model
AU - Cang, Ruijin
AU - Li, Hechao
AU - Yao, Hope
AU - Jiao, Yang
AU - Ren, Yi
N1 - Funding Information:
This work is partially supported by NSF CMMI under Grant No. 1651147 . R. C. and Y. R. thank the startup funding from Arizona State University , Tempe, United States.
Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2018/7
Y1 - 2018/7
N2 - Direct prediction of material properties from microstructures through statistical models has shown to be a potential approach to accelerating computational material design with large design spaces. However, statistical modeling of highly nonlinear mappings defined on high-dimensional microstructure spaces is known to be data-demanding. Thus, the added value of such predictive models diminishes in common cases where material samples (in forms of 2D or 3D microstructures) become costly to acquire either experimentally or computationally. To this end, we propose a generative machine learning model that creates an arbitrary amount of artificial material samples with negligible computation cost, when trained on only a limited amount of authentic samples. The key contribution of this work is the introduction of a morphology constraint to the training of the generative model, that enforces the resultant artificial material samples to have the same morphology distribution as the authentic ones. We show empirically that the proposed model creates artificial samples that better match with the authentic ones in material property distributions than those generated from a state-of-the-art Markov Random Field model, and thus is more effective at improving the prediction performance of a predictive structure-property model.
AB - Direct prediction of material properties from microstructures through statistical models has shown to be a potential approach to accelerating computational material design with large design spaces. However, statistical modeling of highly nonlinear mappings defined on high-dimensional microstructure spaces is known to be data-demanding. Thus, the added value of such predictive models diminishes in common cases where material samples (in forms of 2D or 3D microstructures) become costly to acquire either experimentally or computationally. To this end, we propose a generative machine learning model that creates an arbitrary amount of artificial material samples with negligible computation cost, when trained on only a limited amount of authentic samples. The key contribution of this work is the introduction of a morphology constraint to the training of the generative model, that enforces the resultant artificial material samples to have the same morphology distribution as the authentic ones. We show empirically that the proposed model creates artificial samples that better match with the authentic ones in material property distributions than those generated from a state-of-the-art Markov Random Field model, and thus is more effective at improving the prediction performance of a predictive structure-property model.
KW - Deep learning
KW - Generative models
KW - Integrated computational material engineering
KW - Structure-property mapping
UR - http://www.scopus.com/inward/record.url?scp=85045220619&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85045220619&partnerID=8YFLogxK
U2 - 10.1016/j.commatsci.2018.03.074
DO - 10.1016/j.commatsci.2018.03.074
M3 - Article
AN - SCOPUS:85045220619
SN - 0927-0256
VL - 150
SP - 212
EP - 221
JO - Computational Materials Science
JF - Computational Materials Science
ER -