Inferring low-dimensional microstructure representations using convolutional neural networks

Lubbers, Nicholas; Lookman, Turab; Barros, Kipton

doi:10.1103/PhysRevE.96.052111

Title: Inferring low-dimensional microstructure representations using convolutional neural networks

Journal Article · Thu Nov 09 00:00:00 EST 2017 · Physical Review E

DOI:https://doi.org/10.1103/PhysRevE.96.052111· OSTI ID:1485399

Lubbers, Nicholas ^[1]; Lookman, Turab ^[2]; Barros, Kipton ^[2]

Boston Univ., MA (United States). Dept. of Physics; Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

We apply here recent advances in machine learning and computer vision to a central problem in materials informatics: the statistical representation of microstructural images. We use activations in a pretrained convolutional neural network to provide a high-dimensional characterization of a set of synthetic microstructural images. Next, we use manifold learning to obtain a low-dimensional embedding of this statistical characterization. We show that the low-dimensional embedding extracts the parameters used to generate the images. Finally, according to a variety of metrics, the convolutional neural network method yields dramatically better embeddings than the analogous method derived from two-point correlations alone.

View Accepted Manuscript (DOE)

View Accepted Manuscript (Publisher)

Cite

Export

Save

Research Organization:: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE; LANL Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: AC52-06NA25396

OSTI ID:: 1485399

Alternate ID(s):: OSTI ID: 1408180

Report Number(s):: LA-UR-16-27229

Journal Information:: Physical Review E, Vol. 96, Issue 5; ISSN 2470-0045

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 67 works

Citation information provided by
Web of Science

References (49)

Microstructure sensitive design for performance optimization Fullwood, David T.; Niezgoda, Stephen R.; Adams, Brent L. Progress in Materials Science, Vol. 55, Issue 6 https://doi.org/10.1016/j.pmatsci.2009.08.002	journal	August 2010
Delineation of the space of 2-point correlations in a composite material system Niezgoda, S. R.; Fullwood, D. T.; Kalidindi, S. R. Acta Materialia, Vol. 56, Issue 18 https://doi.org/10.1016/j.actamat.2008.07.005	journal	October 2008
Computational microstructure characterization and reconstruction for stochastic multiscale material design Liu, Yu; Steven Greene, M.; Chen, Wei Computer-Aided Design, Vol. 45, Issue 1 https://doi.org/10.1016/j.cad.2012.03.007	journal	January 2013
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Accelerated search for materials with targeted properties by adaptive design Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms11241	journal	April 2016
A Global Geometric Framework for Nonlinear Dimensionality Reduction Tenenbaum, J. B. Science, Vol. 290, Issue 5500 https://doi.org/10.1126/science.290.5500.2319	journal	December 2000
Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis Kruskal, J. B. Psychometrika, Vol. 29, Issue 1 https://doi.org/10.1007/BF02289565	journal	March 1964
A predictive machine learning approach for microstructure optimization and materials design Liu, Ruoqian; Kumar, Abhishek; Chen, Zhengzhang Scientific Reports, Vol. 5, Issue 1 https://doi.org/10.1038/srep11551	journal	June 2015
Modeling heterogeneous materials via two-point correlation functions: Basic principles Jiao, Y.; Stillinger, F. H.; Torquato, S. Physical Review E, Vol. 76, Issue 3 https://doi.org/10.1103/PhysRevE.76.031110	journal	September 2007
Microstructural degeneracy associated with a two-point correlation function and its information content Gommes, C. J.; Jiao, Y.; Torquato, S. Physical Review E, Vol. 85, Issue 5 https://doi.org/10.1103/PhysRevE.85.051140	journal	May 2012
Three-Dimensional Characterization of Microstructure by Electron Back-Scatter Diffraction Rollett, Anthony D.; Lee, S. -B.; Campman, R. Annual Review of Materials Research, Vol. 37, Issue 1 https://doi.org/10.1146/annurev.matsci.37.052506.084401	journal	August 2007
Predictions of effective physical properties of complex multiphase materials Wang, M.; Pan, N. Materials Science and Engineering: R: Reports, Vol. 63, Issue 1 https://doi.org/10.1016/j.mser.2008.07.001	journal	December 2008
Optimal Design of Heterogeneous Materials Torquato, S. Annual Review of Materials Research, Vol. 40, Issue 1 https://doi.org/10.1146/annurev-matsci-070909-104517	journal	June 2010
Image driven machine learning methods for microstructure recognition Chowdhury, Aritra; Kautz, Elizabeth; Yener, Bülent Computational Materials Science, Vol. 123 https://doi.org/10.1016/j.commatsci.2016.05.034	journal	October 2016
An image synthesizer Perlin, Ken ACM SIGGRAPH Computer Graphics, Vol. 19, Issue 3 https://doi.org/10.1145/325165.325247	journal	July 1985
Big–deep–smart data in imaging for guiding materials design Kalinin, Sergei V.; Sumpter, Bobby G.; Archibald, Richard K. Nature Materials, Vol. 14, Issue 10 https://doi.org/10.1038/nmat4395	journal	September 2015
Geometrical ambiguity of pair statistics. II. Heterogeneous media Jiao, Yang; Stillinger, Frank H.; Torquato, Salvatore Physical Review E, Vol. 82, Issue 1 https://doi.org/10.1103/PhysRevE.82.011106	journal	July 2010
Descriptor-based methodology for statistical characterization and 3D reconstruction of microstructural materials Xu, Hongyi; Dikin, Dmitriy A.; Burkhart, Craig Computational Materials Science, Vol. 85 https://doi.org/10.1016/j.commatsci.2013.12.046	journal	April 2014
Geometrical ambiguity of pair statistics: Point configurations Jiao, Y.; Stillinger, F. H.; Torquato, S. Physical Review E, Vol. 81, Issue 1 https://doi.org/10.1103/PhysRevE.81.011105	journal	January 2010
Stable-phase method for hierarchical annealing in the reconstruction of porous media images Chen, DongDong; Teng, Qizhi; He, Xiaohai Physical Review E, Vol. 89, Issue 1 https://doi.org/10.1103/PhysRevE.89.013305	journal	January 2014
ImageNet Large Scale Visual Recognition Challenge Russakovsky, Olga; Deng, Jia; Su, Hao International Journal of Computer Vision, Vol. 115, Issue 3 https://doi.org/10.1007/s11263-015-0816-y	journal	April 2015
Group Invariant Scattering Mallat, Stéphane Communications on Pure and Applied Mathematics, Vol. 65, Issue 10 https://doi.org/10.1002/cpa.21413	journal	July 2012
Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructures DeCost, Brian L.; Francis, Toby; Holm, Elizabeth A. Acta Materialia, Vol. 133 https://doi.org/10.1016/j.actamat.2017.05.014	journal	July 2017
Improved reconstructions of random media using dilation and erosion processes Zachary, Chase E.; Torquato, Salvatore Physical Review E, Vol. 84, Issue 5 https://doi.org/10.1103/PhysRevE.84.056102	journal	November 2011
Novel microstructure quantification framework for databasing, visualization, and analysis of microstructure data Niezgoda, Stephen R.; Kanjarla, Anand K.; Kalidindi, Surya R. Integrating Materials and Manufacturing Innovation, Vol. 2, Issue 1 https://doi.org/10.1186/2193-9772-2-3	journal	July 2013
Stochastic microstructure characterization and reconstruction via supervised learning Bostanabad, Ramin; Bui, Anh Tuan; Xie, Wei Acta Materialia, Vol. 103 https://doi.org/10.1016/j.actamat.2015.09.044	journal	January 2016
Using microstructure reconstruction to model mechanical behavior in complex microstructures Kumar, H.; Briant, C. L.; Curtin, W. A. Mechanics of Materials, Vol. 38, Issue 8-10 https://doi.org/10.1016/j.mechmat.2005.06.030	journal	August 2006
A superior descriptor of random textures and its predictive capacity Jiao, Y.; Stillinger, F. H.; Torquato, S. Proceedings of the National Academy of Sciences, Vol. 106, Issue 42 https://doi.org/10.1073/pnas.0905919106	journal	October 2009
Gradient-based learning applied to document recognition Lecun, Y.; Bottou, L.; Bengio, Y. Proceedings of the IEEE, Vol. 86, Issue 11 https://doi.org/10.1109/5.726791	journal	January 1998
Classification and reconstruction of three-dimensional microstructures using support vector machines Sundararaghavan, Veeraraghavan; Zabaras, Nicholas Computational Materials Science, Vol. 32, Issue 2 https://doi.org/10.1016/j.commatsci.2004.07.004	journal	February 2005
Nonlinear Dimensionality Reduction by Locally Linear Embedding Roweis, S. T. Science, Vol. 290, Issue 5500 https://doi.org/10.1126/science.290.5500.2323	journal	December 2000
Orientation imaging: The emergence of a new microscopy Adams, Brent L.; Wright, Stuart I.; Kunze, Karsten Metallurgical Transactions A, Vol. 24, Issue 4 https://doi.org/10.1007/BF02656503	journal	April 1993
Informatics and data science in materials microscopy Voyles, Paul M. Current Opinion in Solid State and Materials Science, Vol. 21, Issue 3 https://doi.org/10.1016/j.cossms.2016.10.001	journal	June 2017
Density of States for a Specified Correlation Function and the Energy Landscape Gommes, C. J.; Jiao, Y.; Torquato, S. Physical Review Letters, Vol. 108, Issue 8 https://doi.org/10.1103/PhysRevLett.108.080601	journal	February 2012
Microstructure informatics using higher-order statistics and efficient data-mining protocols Kalidindi, Surya R.; Niezgoda, Stephen R.; Salem, Ayman A. JOM, Vol. 63, Issue 4 https://doi.org/10.1007/s11837-011-0057-7	journal	April 2011
The elements of statistical learning: data mining, inference and prediction Franklin, James The Mathematical Intelligencer, Vol. 27, Issue 2 https://doi.org/10.1007/BF02985802	journal	March 2005
Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials Kalidindi, Surya R. International Materials Reviews, Vol. 60, Issue 3 https://doi.org/10.1179/1743280414Y.0000000043	journal	October 2014
Improving pattern reconstruction using directional correlation functions Gerke, Kirill M.; Karsanina, Marina V.; Vasilyev, Roman V. EPL (Europhysics Letters), Vol. 106, Issue 6 https://doi.org/10.1209/0295-5075/106/66002	journal	June 2014
Microstructure reconstructions from 2-point statistics using phase-recovery algorithms Fullwood, David T.; Niezgoda, Stephen R.; Kalidindi, Surya R. Acta Materialia, Vol. 56, Issue 5 https://doi.org/10.1016/j.actamat.2007.10.044	journal	March 2008
A computer vision approach for automated analysis and classification of microstructural image data DeCost, Brian L.; Holm, Elizabeth A. Computational Materials Science, Vol. 110 https://doi.org/10.1016/j.commatsci.2015.08.011	journal	December 2015
Insights into twinning in Mg AZ31: A combined EBSD and machine learning study Orme, Andrew D.; Chelladurai, Isaac; Rampton, Travis M. Computational Materials Science, Vol. 124 https://doi.org/10.1016/j.commatsci.2016.08.011	journal	November 2016
ImageNet Large Scale Visual Recognition Challenge Jia, Deng,; Andrej, Karpathy,; Sean, Ma, The University of North Carolina at Chapel Hill University Libraries https://doi.org/10.17615/009h-3a34	text	January 2015
Deep Learning Ganatra, Sanket Zenodo https://doi.org/10.5281/zenodo.1189359	text	January 2018
The Elements of Statistical Learning: Data Mining, Inference, and Prediction John Lu, Z. Q. Journal of the Royal Statistical Society: Series A (Statistics in Society), Vol. 173, Issue 3 https://doi.org/10.1111/j.1467-985x.2010.00646_6.x	journal	January 2010
Geometrical Ambiguity of Pair Statistics. I. Point Configurations Jiao, Y.; Stillinger, F. H.; Torquato, S. arXiv https://doi.org/10.48550/arxiv.0908.1366	text	January 2009
Geometrical Ambiguity of Pair Statistics. II. Heterogeneous Media Jiao, Yang; Stillinger, Frank H.; Torquato, Sal arXiv https://doi.org/10.48550/arxiv.1007.1374	text	January 2010
Group Invariant Scattering Mallat, Stéphane arXiv https://doi.org/10.48550/arxiv.1101.2286	preprint	January 2011
A Superior Descriptor of Random Textures and Its Predictive Capacity Jiao, Yang; Torquato, Sal; Stillinger, Frank H. arXiv https://doi.org/10.48550/arxiv.1201.0710	text	January 2012
Density of States for a Specified Correlation Function and the Energy Landscape Gommes, Cedric; Jiao, Yang; Torquato, Salvatore arXiv https://doi.org/10.48550/arxiv.1201.1142	text	January 2012

Cited By (12)

Deep Learning to Speed up the Development of Structure–Property Relations For Hexagonal Boron Nitride and Graphene Hundi, Prabhas; Shahsavari, Rouzbeh Small, Vol. 15, Issue 19 https://doi.org/10.1002/smll.201900656	journal	April 2019
Transfer learning of deep material network for seamless structure–property predictions Liu, Zeliang; Wu, C. T.; Koishi, M. Computational Mechanics, Vol. 64, Issue 2 https://doi.org/10.1007/s00466-019-01704-4	journal	April 2019
Clustering discretization methods for generation of material performance databases in machine learning and design optimization Li, Hengyang; Kafka, Orion L.; Gao, Jiaying Computational Mechanics, Vol. 64, Issue 2 https://doi.org/10.1007/s00466-019-01716-0	journal	May 2019
Automated defect analysis in electron microscopic images Li, Wei; Field, Kevin G.; Morgan, Dane npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0093-8	journal	July 2018
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions Li, Xiaolin; Zhang, Yichi; Zhao, He Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-31571-7	journal	September 2018
Precise algorithms to compute surface correlation functions of two-phase heterogeneous media and their applications Ma, Zheng; Torquato, Salvatore Physical Review E, Vol. 98, Issue 1 https://doi.org/10.1103/physreve.98.013307	journal	July 2018
Multifunctionality of particulate composites via cross-property maps Torquato, S.; Chen, D. Physical Review Materials, Vol. 2, Issue 9 https://doi.org/10.1103/physrevmaterials.2.095603	journal	September 2018
Microstructural Materials Design Via Deep Adversarial Learning Methodology Yang, Zijiang; Li, Xiaolin; Catherine Brinson, L. Journal of Mechanical Design, Vol. 140, Issue 11 https://doi.org/10.1115/1.4041371	journal	October 2018
A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian J. Frontiers in Materials, Vol. 6 https://doi.org/10.3389/fmats.2019.00110	journal	May 2019
Modeling Macroscopic Material Behavior With Machine Learning Algorithms Trained by Micromechanical Simulations Reimann, Denise; Nidadavolu, Kapil; ul Hassan, Hamad Frontiers in Materials, Vol. 6 https://doi.org/10.3389/fmats.2019.00181	journal	August 2019
A review of the application of machine learning and data mining approaches in continuum materials mechanics Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian J. TUHH Universitätsbibliothek https://doi.org/10.15480/882.2309	text	January 2019
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions Li, Xiaolin; Zhang, Yichi; Zhao, He arXiv https://doi.org/10.48550/arxiv.1805.02784	preprint	January 2018