Inferring low-dimensional microstructure representations using convolutional neural networks
Abstract
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.
- Authors:
-
- 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)
- Publication Date:
- Research Org.:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE; LANL Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1485399
- Alternate Identifier(s):
- OSTI ID: 1408180
- Report Number(s):
- LA-UR-16-27229
Journal ID: ISSN 2470-0045
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Physical Review E
- Additional Journal Information:
- Journal Volume: 96; Journal Issue: 5; Journal ID: ISSN 2470-0045
- Publisher:
- American Physical Society (APS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; microstructure; coarse graining; machine learning
Citation Formats
Lubbers, Nicholas, Lookman, Turab, and Barros, Kipton. Inferring low-dimensional microstructure representations using convolutional neural networks. United States: N. p., 2017.
Web. doi:10.1103/PhysRevE.96.052111.
Lubbers, Nicholas, Lookman, Turab, & Barros, Kipton. Inferring low-dimensional microstructure representations using convolutional neural networks. United States. https://doi.org/10.1103/PhysRevE.96.052111
Lubbers, Nicholas, Lookman, Turab, and Barros, Kipton. Thu .
"Inferring low-dimensional microstructure representations using convolutional neural networks". United States. https://doi.org/10.1103/PhysRevE.96.052111. https://www.osti.gov/servlets/purl/1485399.
@article{osti_1485399,
title = {Inferring low-dimensional microstructure representations using convolutional neural networks},
author = {Lubbers, Nicholas and Lookman, Turab and Barros, Kipton},
abstractNote = {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.},
doi = {10.1103/PhysRevE.96.052111},
journal = {Physical Review E},
number = 5,
volume = 96,
place = {United States},
year = {Thu Nov 09 00:00:00 EST 2017},
month = {Thu Nov 09 00:00:00 EST 2017}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 67 works
Citation information provided by
Web of Science
Web of Science
Figures / Tables:
FIG. 1: (Color online) Texture synthesis of materials microstructures using the CNN algorithm from [37]. The CNN synthesizes each “Reconstruction” image from a single “Original” image. (Image attributions listed in Appendix A.)
All figures and tables
(13 total)
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Microstructure sensitive design for performance optimization
journal, August 2010
- Fullwood, David T.; Niezgoda, Stephen R.; Adams, Brent L.
- Progress in Materials Science, Vol. 55, Issue 6
Delineation of the space of 2-point correlations in a composite material system
journal, October 2008
- Niezgoda, S. R.; Fullwood, D. T.; Kalidindi, S. R.
- Acta Materialia, Vol. 56, Issue 18
Computational microstructure characterization and reconstruction for stochastic multiscale material design
journal, January 2013
- Liu, Yu; Steven Greene, M.; Chen, Wei
- Computer-Aided Design, Vol. 45, Issue 1
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Accelerated search for materials with targeted properties by adaptive design
journal, April 2016
- Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John
- Nature Communications, Vol. 7, Issue 1
A Global Geometric Framework for Nonlinear Dimensionality Reduction
journal, December 2000
- Tenenbaum, J. B.
- Science, Vol. 290, Issue 5500
Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
journal, March 1964
- Kruskal, J. B.
- Psychometrika, Vol. 29, Issue 1
A predictive machine learning approach for microstructure optimization and materials design
journal, June 2015
- Liu, Ruoqian; Kumar, Abhishek; Chen, Zhengzhang
- Scientific Reports, Vol. 5, Issue 1
Modeling heterogeneous materials via two-point correlation functions: Basic principles
journal, September 2007
- Jiao, Y.; Stillinger, F. H.; Torquato, S.
- Physical Review E, Vol. 76, Issue 3
Microstructural degeneracy associated with a two-point correlation function and its information content
journal, May 2012
- Gommes, C. J.; Jiao, Y.; Torquato, S.
- Physical Review E, Vol. 85, Issue 5
Three-Dimensional Characterization of Microstructure by Electron Back-Scatter Diffraction
journal, August 2007
- Rollett, Anthony D.; Lee, S. -B.; Campman, R.
- Annual Review of Materials Research, Vol. 37, Issue 1
Predictions of effective physical properties of complex multiphase materials
journal, December 2008
- Wang, M.; Pan, N.
- Materials Science and Engineering: R: Reports, Vol. 63, Issue 1
Optimal Design of Heterogeneous Materials
journal, June 2010
- Torquato, S.
- Annual Review of Materials Research, Vol. 40, Issue 1
Image driven machine learning methods for microstructure recognition
journal, October 2016
- Chowdhury, Aritra; Kautz, Elizabeth; Yener, Bülent
- Computational Materials Science, Vol. 123
An image synthesizer
journal, July 1985
- Perlin, Ken
- ACM SIGGRAPH Computer Graphics, Vol. 19, Issue 3
Big–deep–smart data in imaging for guiding materials design
journal, September 2015
- Kalinin, Sergei V.; Sumpter, Bobby G.; Archibald, Richard K.
- Nature Materials, Vol. 14, Issue 10
Geometrical ambiguity of pair statistics. II. Heterogeneous media
journal, July 2010
- Jiao, Yang; Stillinger, Frank H.; Torquato, Salvatore
- Physical Review E, Vol. 82, Issue 1
Descriptor-based methodology for statistical characterization and 3D reconstruction of microstructural materials
journal, April 2014
- Xu, Hongyi; Dikin, Dmitriy A.; Burkhart, Craig
- Computational Materials Science, Vol. 85
Geometrical ambiguity of pair statistics: Point configurations
journal, January 2010
- Jiao, Y.; Stillinger, F. H.; Torquato, S.
- Physical Review E, Vol. 81, Issue 1
Stable-phase method for hierarchical annealing in the reconstruction of porous media images
journal, January 2014
- Chen, DongDong; Teng, Qizhi; He, Xiaohai
- Physical Review E, Vol. 89, Issue 1
ImageNet Large Scale Visual Recognition Challenge
journal, April 2015
- Russakovsky, Olga; Deng, Jia; Su, Hao
- International Journal of Computer Vision, Vol. 115, Issue 3
Group Invariant Scattering
journal, July 2012
- Mallat, Stéphane
- Communications on Pure and Applied Mathematics, Vol. 65, Issue 10
Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructures
journal, July 2017
- DeCost, Brian L.; Francis, Toby; Holm, Elizabeth A.
- Acta Materialia, Vol. 133
Improved reconstructions of random media using dilation and erosion processes
journal, November 2011
- Zachary, Chase E.; Torquato, Salvatore
- Physical Review E, Vol. 84, Issue 5
Novel microstructure quantification framework for databasing, visualization, and analysis of microstructure data
journal, July 2013
- Niezgoda, Stephen R.; Kanjarla, Anand K.; Kalidindi, Surya R.
- Integrating Materials and Manufacturing Innovation, Vol. 2, Issue 1
Stochastic microstructure characterization and reconstruction via supervised learning
journal, January 2016
- Bostanabad, Ramin; Bui, Anh Tuan; Xie, Wei
- Acta Materialia, Vol. 103
Using microstructure reconstruction to model mechanical behavior in complex microstructures
journal, August 2006
- Kumar, H.; Briant, C. L.; Curtin, W. A.
- Mechanics of Materials, Vol. 38, Issue 8-10
A superior descriptor of random textures and its predictive capacity
journal, October 2009
- Jiao, Y.; Stillinger, F. H.; Torquato, S.
- Proceedings of the National Academy of Sciences, Vol. 106, Issue 42
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
Classification and reconstruction of three-dimensional microstructures using support vector machines
journal, February 2005
- Sundararaghavan, Veeraraghavan; Zabaras, Nicholas
- Computational Materials Science, Vol. 32, Issue 2
Nonlinear Dimensionality Reduction by Locally Linear Embedding
journal, December 2000
- Roweis, S. T.
- Science, Vol. 290, Issue 5500
Orientation imaging: The emergence of a new microscopy
journal, April 1993
- Adams, Brent L.; Wright, Stuart I.; Kunze, Karsten
- Metallurgical Transactions A, Vol. 24, Issue 4
Informatics and data science in materials microscopy
journal, June 2017
- Voyles, Paul M.
- Current Opinion in Solid State and Materials Science, Vol. 21, Issue 3
Density of States for a Specified Correlation Function and the Energy Landscape
journal, February 2012
- Gommes, C. J.; Jiao, Y.; Torquato, S.
- Physical Review Letters, Vol. 108, Issue 8
Microstructure informatics using higher-order statistics and efficient data-mining protocols
journal, April 2011
- Kalidindi, Surya R.; Niezgoda, Stephen R.; Salem, Ayman A.
- JOM, Vol. 63, Issue 4
The elements of statistical learning: data mining, inference and prediction
journal, March 2005
- Franklin, James
- The Mathematical Intelligencer, Vol. 27, Issue 2
Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials
journal, October 2014
- Kalidindi, Surya R.
- International Materials Reviews, Vol. 60, Issue 3
Improving pattern reconstruction using directional correlation functions
journal, June 2014
- Gerke, Kirill M.; Karsanina, Marina V.; Vasilyev, Roman V.
- EPL (Europhysics Letters), Vol. 106, Issue 6
Microstructure reconstructions from 2-point statistics using phase-recovery algorithms
journal, March 2008
- Fullwood, David T.; Niezgoda, Stephen R.; Kalidindi, Surya R.
- Acta Materialia, Vol. 56, Issue 5
A computer vision approach for automated analysis and classification of microstructural image data
journal, December 2015
- DeCost, Brian L.; Holm, Elizabeth A.
- Computational Materials Science, Vol. 110
Insights into twinning in Mg AZ31: A combined EBSD and machine learning study
journal, November 2016
- Orme, Andrew D.; Chelladurai, Isaac; Rampton, Travis M.
- Computational Materials Science, Vol. 124
ImageNet Large Scale Visual Recognition Challenge
text, January 2015
- Jia, Deng,; Andrej, Karpathy,; Sean, Ma,
- The University of North Carolina at Chapel Hill University Libraries
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
journal, January 2010
- John Lu, Z. Q.
- Journal of the Royal Statistical Society: Series A (Statistics in Society), Vol. 173, Issue 3
Geometrical Ambiguity of Pair Statistics. I. Point Configurations
text, January 2009
- Jiao, Y.; Stillinger, F. H.; Torquato, S.
- arXiv
Geometrical Ambiguity of Pair Statistics. II. Heterogeneous Media
text, January 2010
- Jiao, Yang; Stillinger, Frank H.; Torquato, Sal
- arXiv
A Superior Descriptor of Random Textures and Its Predictive Capacity
text, January 2012
- Jiao, Yang; Torquato, Sal; Stillinger, Frank H.
- arXiv
Density of States for a Specified Correlation Function and the Energy Landscape
text, January 2012
- Gommes, Cedric; Jiao, Yang; Torquato, Salvatore
- arXiv
Works referencing / citing this record:
Deep Learning to Speed up the Development of Structure–Property Relations For Hexagonal Boron Nitride and Graphene
journal, April 2019
- Hundi, Prabhas; Shahsavari, Rouzbeh
- Small, Vol. 15, Issue 19
Transfer learning of deep material network for seamless structure–property predictions
journal, April 2019
- Liu, Zeliang; Wu, C. T.; Koishi, M.
- Computational Mechanics, Vol. 64, Issue 2
Clustering discretization methods for generation of material performance databases in machine learning and design optimization
journal, May 2019
- Li, Hengyang; Kafka, Orion L.; Gao, Jiaying
- Computational Mechanics, Vol. 64, Issue 2
Automated defect analysis in electron microscopic images
journal, July 2018
- Li, Wei; Field, Kevin G.; Morgan, Dane
- npj Computational Materials, Vol. 4, Issue 1
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions
journal, September 2018
- Li, Xiaolin; Zhang, Yichi; Zhao, He
- Scientific Reports, Vol. 8, Issue 1
Precise algorithms to compute surface correlation functions of two-phase heterogeneous media and their applications
journal, July 2018
- Ma, Zheng; Torquato, Salvatore
- Physical Review E, Vol. 98, Issue 1
Multifunctionality of particulate composites via cross-property maps
journal, September 2018
- Torquato, S.; Chen, D.
- Physical Review Materials, Vol. 2, Issue 9
Microstructural Materials Design Via Deep Adversarial Learning Methodology
journal, October 2018
- Yang, Zijiang; Li, Xiaolin; Catherine Brinson, L.
- Journal of Mechanical Design, Vol. 140, Issue 11
A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics
journal, May 2019
- Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian J.
- Frontiers in Materials, Vol. 6
Modeling Macroscopic Material Behavior With Machine Learning Algorithms Trained by Micromechanical Simulations
journal, August 2019
- Reimann, Denise; Nidadavolu, Kapil; ul Hassan, Hamad
- Frontiers in Materials, Vol. 6
A review of the application of machine learning and data mining approaches in continuum materials mechanics
text, January 2019
- Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian J.
- TUHH Universitätsbibliothek
A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions
preprint, January 2018
- Li, Xiaolin; Zhang, Yichi; Zhao, He
- arXiv
Figures / Tables found in this record:
Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.