skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: 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:
 [1];  [2];  [2]
  1. Boston Univ., MA (United States). Dept. of Physics; Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. 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. doi:10.1103/PhysRevE.96.052111.
Lubbers, Nicholas, Lookman, Turab, and Barros, Kipton. Thu . "Inferring low-dimensional microstructure representations using convolutional neural networks". United States. doi: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 = {2017},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 16 works
Citation information provided by
Web of Science

Figures / Tables:

FIG. 1 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.)

Save / Share:

Works referenced in this record:

Microstructure sensitive design for performance optimization
journal, August 2010


Delineation of the space of 2-point correlations in a composite material system
journal, October 2008


Computational microstructure characterization and reconstruction for stochastic multiscale material design
journal, January 2013


Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

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
  • DOI: 10.1038/ncomms11241

A Global Geometric Framework for Nonlinear Dimensionality Reduction
journal, December 2000


Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
journal, March 1964


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
  • DOI: 10.1038/srep11551

Modeling heterogeneous materials via two-point correlation functions: Basic principles
journal, September 2007


Microstructural degeneracy associated with a two-point correlation function and its information content
journal, May 2012


Three-Dimensional Characterization of Microstructure by Electron Back-Scatter Diffraction
journal, August 2007


Predictions of effective physical properties of complex multiphase materials
journal, December 2008


Optimal Design of Heterogeneous Materials
journal, June 2010


Image driven machine learning methods for microstructure recognition
journal, October 2016


An image synthesizer
journal, July 1985


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
  • DOI: 10.1038/nmat4395

Geometrical ambiguity of pair statistics. II. Heterogeneous media
journal, July 2010


Descriptor-based methodology for statistical characterization and 3D reconstruction of microstructural materials
journal, April 2014


Geometrical ambiguity of pair statistics: Point configurations
journal, January 2010


Stable-phase method for hierarchical annealing in the reconstruction of porous media images
journal, January 2014


ImageNet Large Scale Visual Recognition Challenge
journal, April 2015

  • Russakovsky, Olga; Deng, Jia; Su, Hao
  • International Journal of Computer Vision, Vol. 115, Issue 3
  • DOI: 10.1007/s11263-015-0816-y

Group Invariant Scattering
journal, July 2012

  • Mallat, Stéphane
  • Communications on Pure and Applied Mathematics, Vol. 65, Issue 10
  • DOI: 10.1002/cpa.21413

Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructures
journal, July 2017


Improved reconstructions of random media using dilation and erosion processes
journal, November 2011


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
  • DOI: 10.1186/2193-9772-2-3

Stochastic microstructure characterization and reconstruction via supervised learning
journal, January 2016


Using microstructure reconstruction to model mechanical behavior in complex microstructures
journal, August 2006


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
  • DOI: 10.1073/pnas.0905919106

Gradient-based learning applied to document recognition
journal, January 1998

  • Lecun, Y.; Bottou, L.; Bengio, Y.
  • Proceedings of the IEEE, Vol. 86, Issue 11
  • DOI: 10.1109/5.726791

Classification and reconstruction of three-dimensional microstructures using support vector machines
journal, February 2005


Nonlinear Dimensionality Reduction by Locally Linear Embedding
journal, December 2000


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
  • DOI: 10.1007/BF02656503

Informatics and data science in materials microscopy
journal, June 2017


Density of States for a Specified Correlation Function and the Energy Landscape
journal, February 2012


Microstructure informatics using higher-order statistics and efficient data-mining protocols
journal, April 2011


The elements of statistical learning: data mining, inference and prediction
journal, March 2005

  • Franklin, James
  • The Mathematical Intelligencer, Vol. 27, Issue 2
  • DOI: 10.1007/BF02985802

Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials
journal, October 2014


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
  • DOI: 10.1209/0295-5075/106/66002

Microstructure reconstructions from 2-point statistics using phase-recovery algorithms
journal, March 2008


A computer vision approach for automated analysis and classification of microstructural image data
journal, December 2015


Insights into twinning in Mg AZ31: A combined EBSD and machine learning study
journal, November 2016


    Works referencing / citing this record:

    Transfer learning of deep material network for seamless structure–property predictions
    journal, April 2019


    Clustering discretization methods for generation of material performance databases in machine learning and design optimization
    journal, May 2019


    Automated defect analysis in electron microscopic images
    journal, July 2018