A Comparative Study of the Efficacy of Local/Global and Parametric/Nonparametric Machine Learning Methods for Establishing Structure–Property Linkages in High-Contrast 3D Elastic Composites
Abstract
Reduced-order structure–property (S-P) linkages play a pivotal role in the tailored design of materials for advanced engineering components. There is a critical need to distill these from the simulation datasets aggregated using sophisticated, computationally expensive, physics-based numerical tools (e.g., finite element methods). The recent emergence of materials data science approaches has opened new avenues for addressing this challenge. In this paper, we critically compare the relative merits of the application of four distinct machine learning approaches for their efficacy in extracting microstructure-property linkages from the finite element simulation data aggregated on high-contrast elastic composites with different microstructures. The machine learning approaches selected for the study have included different combinations of local/global and parametric/nonparametric approaches. Furthermore, the nonparametric approaches selected for this study are based on Gaussian Process (GP) models that allow for a formal treatment of uncertainty quantification in the predicted values. The predictive performances of these different approaches have been compared against each other using rigorous cross-validation error metrics. Furthermore, their sensitivity to both the dataset size and dimensionality has been investigated.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Georgia Inst. of Technology, Atlanta, GA (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1559631
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Integrating Materials and Manufacturing Innovation
- Additional Journal Information:
- Journal Volume: 8; Journal Issue: 2; Journal ID: ISSN 2193-9764
- Publisher:
- Springer
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE
Citation Formats
Fernandez-Zelaia, Patxi, Yabansu, Yuksel C., and Kalidindi, Surya R. A Comparative Study of the Efficacy of Local/Global and Parametric/Nonparametric Machine Learning Methods for Establishing Structure–Property Linkages in High-Contrast 3D Elastic Composites. United States: N. p., 2019.
Web. doi:10.1007/s40192-019-00129-4.
Fernandez-Zelaia, Patxi, Yabansu, Yuksel C., & Kalidindi, Surya R. A Comparative Study of the Efficacy of Local/Global and Parametric/Nonparametric Machine Learning Methods for Establishing Structure–Property Linkages in High-Contrast 3D Elastic Composites. United States. https://doi.org/10.1007/s40192-019-00129-4
Fernandez-Zelaia, Patxi, Yabansu, Yuksel C., and Kalidindi, Surya R. Sat .
"A Comparative Study of the Efficacy of Local/Global and Parametric/Nonparametric Machine Learning Methods for Establishing Structure–Property Linkages in High-Contrast 3D Elastic Composites". United States. https://doi.org/10.1007/s40192-019-00129-4. https://www.osti.gov/servlets/purl/1559631.
@article{osti_1559631,
title = {A Comparative Study of the Efficacy of Local/Global and Parametric/Nonparametric Machine Learning Methods for Establishing Structure–Property Linkages in High-Contrast 3D Elastic Composites},
author = {Fernandez-Zelaia, Patxi and Yabansu, Yuksel C. and Kalidindi, Surya R.},
abstractNote = {Reduced-order structure–property (S-P) linkages play a pivotal role in the tailored design of materials for advanced engineering components. There is a critical need to distill these from the simulation datasets aggregated using sophisticated, computationally expensive, physics-based numerical tools (e.g., finite element methods). The recent emergence of materials data science approaches has opened new avenues for addressing this challenge. In this paper, we critically compare the relative merits of the application of four distinct machine learning approaches for their efficacy in extracting microstructure-property linkages from the finite element simulation data aggregated on high-contrast elastic composites with different microstructures. The machine learning approaches selected for the study have included different combinations of local/global and parametric/nonparametric approaches. Furthermore, the nonparametric approaches selected for this study are based on Gaussian Process (GP) models that allow for a formal treatment of uncertainty quantification in the predicted values. The predictive performances of these different approaches have been compared against each other using rigorous cross-validation error metrics. Furthermore, their sensitivity to both the dataset size and dimensionality has been investigated.},
doi = {10.1007/s40192-019-00129-4},
journal = {Integrating Materials and Manufacturing Innovation},
number = 2,
volume = 8,
place = {United States},
year = {Sat Jun 01 00:00:00 EDT 2019},
month = {Sat Jun 01 00:00:00 EDT 2019}
}
Web of Science
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
Surrogate Modeling of Computer Experiments With Different Mesh Densities
journal, July 2014
- Tuo, Rui; Wu, C. F. Jeff; Yu, Dan
- Technometrics, Vol. 56, Issue 3
Modeling of two-phase random composite materials by finite element, Mori–Tanaka and strong contrast methods
journal, February 2013
- Mortazavi, Bohayra; Baniassadi, Majid; Bardon, Julien
- Composites Part B: Engineering, Vol. 45, Issue 1
Extraction of Process-Structure Evolution Linkages from X-ray Scattering Measurements Using Dimensionality Reduction and Time Series Analysis
journal, March 2017
- Brough, David B.; Kannan, Abhiram; Haaland, Benjamin
- Integrating Materials and Manufacturing Innovation, Vol. 6, Issue 2
Flexible Correlation Structure for Accurate Prediction and Uncertainty Quantification in Bayesian Gaussian Process Emulation of a Computer Model
journal, January 2017
- Chen, Hao; Loeppky, Jason L.; Welch, William J.
- SIAM/ASA Journal on Uncertainty Quantification, Vol. 5, Issue 1
Structure–property linkages using a data science approach: Application to a non-metallic inclusion/steel composite system
journal, June 2015
- Gupta, Akash; Cecen, Ahmet; Goyal, Sharad
- Acta Materialia, Vol. 91
Estimating mechanical properties from spherical indentation using Bayesian approaches
journal, June 2018
- Fernandez-Zelaia, Patxi; Roshan Joseph, V.; Kalidindi, Surya R.
- Materials & Design, Vol. 147
Statistical calibration and uncertainty quantification of complex machining computer models
journal, January 2019
- Fernandez-Zelaia, Patxi; Melkote, Shreyes N.
- International Journal of Machine Tools and Manufacture, Vol. 136
Quantitative prediction of the aged state of Ni-base superalloys using PCA and tensor regression
journal, February 2019
- Gorgannejad, S.; Reisi Gahrooei, M.; Paynabar, K.
- Acta Materialia, Vol. 165
Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statistics
journal, May 2017
- Paulson, Noah H.; Priddy, Matthew W.; McDowell, David L.
- Acta Materialia, Vol. 129
Process-Structure-Property Relationships for 316L Stainless Steel Fabricated by Additive Manufacturing and Its Implication for Component Engineering
journal, December 2016
- Yang, Nancy; Yee, J.; Zheng, B.
- Journal of Thermal Spray Technology, Vol. 26, Issue 4
A Goal-Oriented, Inverse Decision-Based Design Method to Achieve the Vertical and Horizontal Integration of Models in a Hot Rod Rolling Process Chain
conference, November 2017
- Nellippallil, Anand Balu; Rangaraj, Vignesh; Gautham, B. P.
- ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Volume 2B: 43rd Design Automation Conference
Effective elastic properties of composites with particles of polyhedral shapes
journal, August 2017
- Trofimov, Anton; Drach, Borys; Sevostianov, Igor
- International Journal of Solids and Structures, Vol. 120
BART: Bayesian additive regression trees
journal, March 2010
- Chipman, Hugh A.; George, Edward I.; McCulloch, Robert E.
- The Annals of Applied Statistics, Vol. 4, Issue 1
Establishing structure-property localization linkages for elastic deformation of three-dimensional high contrast composites using deep learning approaches
journal, March 2019
- Yang, Zijiang; Yabansu, Yuksel C.; Jha, Dipendra
- Acta Materialia, Vol. 166
Data-driven reduced order models for effective yield strength and partitioning of strain in multiphase materials
journal, October 2017
- Latypov, Marat I.; Kalidindi, Surya R.
- Journal of Computational Physics, Vol. 346
Extracting knowledge from molecular mechanics simulations of grain boundaries using machine learning
journal, July 2017
- Gomberg, Joshua A.; Medford, Andrew J.; Kalidindi, Surya R.
- Acta Materialia, Vol. 133
Multi-scale modeling of elastic response of three-dimensional voxel-based microstructure datasets using novel DFT-based knowledge systems
journal, April 2010
- Landi, Giacomo; Niezgoda, Stephen R.; Kalidindi, Surya R.
- Acta Materialia, Vol. 58, Issue 7
Representation and calibration of elastic localization kernels for a broad class of cubic polycrystals
journal, August 2015
- Yabansu, Yuksel C.; Kalidindi, Surya R.
- Acta Materialia, Vol. 94
laGP : Large-Scale Spatial Modeling via Local Approximate Gaussian Processes in R
journal, January 2016
- Gramacy, Robert B.
- Journal of Statistical Software, Vol. 72, Issue 1
Present status of amorphous soft magnetic alloys
journal, June 2000
- Hasegawa, Ryusuke
- Journal of Magnetism and Magnetic Materials, Vol. 215-216
Efficient computation of the angularly resolved chord length distributions and lineal path functions in large microstructure datasets
journal, September 2016
- Turner, David M.; Niezgoda, Stephen R.; Kalidindi, Surya R.
- Modelling and Simulation in Materials Science and Engineering, Vol. 24, Issue 7
Computational Design of Hierarchically Structured Materials
journal, August 1997
- Olson, G. B.
- Science, Vol. 277, Issue 5330
Materials Knowledge Systems in Python—a Data Science Framework for Accelerated Development of Hierarchical Materials
journal, March 2017
- Brough, David B.; Wheeler, Daniel; Kalidindi, Surya R.
- Integrating Materials and Manufacturing Innovation, Vol. 6, Issue 1
Local Gaussian Process Approximation for Large Computer Experiments
journal, April 2015
- Gramacy, Robert B.; Apley, Daniel W.
- Journal of Computational and Graphical Statistics, Vol. 24, Issue 2
Effects of particle size, particle/matrix interface adhesion and particle loading on mechanical properties of particulate–polymer composites
journal, September 2008
- Fu, Shao-Yun; Feng, Xi-Qiao; Lauke, Bernd
- Composites Part B: Engineering, Vol. 39, Issue 6
A two-phase self-consistent model for the grid indentation testing of composite materials
journal, December 2017
- Argatov, Ivan I.; Sabina, Federico J.
- International Journal of Engineering Science, Vol. 121
A review on the key issues for lithium-ion battery management in electric vehicles
journal, March 2013
- Lu, Languang; Han, Xuebing; Li, Jianqiu
- Journal of Power Sources, Vol. 226, p. 272-288
Gaussian predictive process models for large spatial data sets
journal, September 2008
- Banerjee, Sudipto; Gelfand, Alan E.; Finley, Andrew O.
- Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 70, Issue 4
A new framework for rotationally invariant two-point spatial correlations in microstructure datasets
journal, October 2018
- Cecen, Ahmet; Yabansu, Yuksel C.; Kalidindi, Surya R.
- Acta Materialia, Vol. 158
Ni-based superalloys for turbine discs
journal, January 1999
- Furrer, David; Fecht, Hans
- JOM, Vol. 51, Issue 1
Robust Locally Weighted Regression and Smoothing Scatterplots
journal, December 1979
- Cleveland, William S.
- Journal of the American Statistical Association, Vol. 74, Issue 368
Size-dependent effective elastic constants of solids containing nano-inhomogeneities with interface stress
journal, July 2005
- Duan, H. L.; Wang, J.; Huang, Z. P.
- Journal of the Mechanics and Physics of Solids, Vol. 53, Issue 7
Inverse molecular design using machine learning: Generative models for matter engineering
journal, July 2018
- Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán
- Science, Vol. 361, Issue 6400
Applied machine learning to predict stress hotspots I: Face centered cubic materials
journal, December 2018
- Mangal, Ankita; Holm, Elizabeth A.
- International Journal of Plasticity, Vol. 111
Principles of geostatistics
journal, December 1963
- Matheron, Georges
- Economic Geology, Vol. 58, Issue 8
The materials innovation ecosystem: A key enabler for the Materials Genome Initiative
journal, April 2016
- McDowell, David L.; Kalidindi, Surya R.
- MRS Bulletin, Vol. 41, Issue 4
Effective conductivity in isotropic heterogeneous media using a strong-contrast statistical continuum theory
journal, January 2009
- Mikdam, A.; Makradi, A.; Ahzi, S.
- Journal of the Mechanics and Physics of Solids, Vol. 57, Issue 1
Bayesian Treed Gaussian Process Models With an Application to Computer Modeling
journal, September 2008
- Gramacy, Robert B.; Lee, Herbert K. H.
- Journal of the American Statistical Association, Vol. 103, Issue 483
A strong contrast homogenization formulation for multi-phase anisotropic materials
journal, June 2008
- Fullwood, David T.; Adams, Brent L.; Kalidindi, Surya R.
- Journal of the Mechanics and Physics of Solids, Vol. 56, Issue 6
Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets
journal, August 2018
- Yang, Zijiang; Yabansu, Yuksel C.; Al-Bahrani, Reda
- Computational Materials Science, Vol. 151
Bayesian approach in predicting mechanical properties of materials: Application to dual phase steels
journal, January 2019
- Jung, Jaimyun; Yoon, Jae Ik; Park, Hyung Keun
- Materials Science and Engineering: A, Vol. 743
Application of spherical indentation and the materials knowledge system framework to establishing microstructure-yield strength linkages from carbon steel scoops excised from high-temperature exposed components
journal, February 2018
- Iskakov, Almambet; Yabansu, Yuksel C.; Rajagopalan, Sudhir
- Acta Materialia, Vol. 144
Convolutional neural networks for atomistic systems
journal, June 2018
- Ryczko, Kevin; Mills, Kyle; Luchak, Iryna
- Computational Materials Science, Vol. 149
Extraction of reduced-order process-structure linkages from phase-field simulations
journal, February 2017
- Yabansu, Yuksel C.; Steinmetz, Philipp; Hötzer, Johannes
- Acta Materialia, Vol. 124
Nickel-Based Superalloys for Advanced Turbine Engines: Chemistry, Microstructure and Properties
journal, March 2006
- Pollock, Tresa M.; Tin, Sammy
- Journal of Propulsion and Power, Vol. 22, Issue 2
Practical Heteroscedastic Gaussian Process Modeling for Large Simulation Experiments
journal, July 2018
- Binois, Mickaël; Gramacy, Robert B.; Ludkovski, Mike
- Journal of Computational and Graphical Statistics, Vol. 27, Issue 4
Composite Gaussian process models for emulating expensive functions
journal, December 2012
- Ba, Shan; Joseph, V. Roshan
- The Annals of Applied Statistics, Vol. 6, Issue 4
Microstructure recognition using convolutional neural networks for prediction of ionic conductivity in ceramics
journal, December 2017
- Kondo, Ruho; Yamakawa, Shunsuke; Masuoka, Yumi
- Acta Materialia, Vol. 141
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
Key computational modeling issues in Integrated Computational Materials Engineering
journal, January 2013
- Panchal, Jitesh H.; Kalidindi, Surya R.; McDowell, David L.
- Computer-Aided Design, Vol. 45, Issue 1
Introduction
book, January 2001
- Hastie, Trevor; Friedman, Jerome; Tibshirani, Robert
- The Elements of Statistical Learning
Design and Analysis of Computer Experiments
journal, November 1989
- Sacks, Jerome; Welch, William J.; Mitchell, Toby J.
- Statistical Science, Vol. 4, Issue 4
Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting
journal, September 1988
- Cleveland, William S.; Devlin, Susan J.
- Journal of the American Statistical Association, Vol. 83, Issue 403
Material structure-property linkages using three-dimensional convolutional neural networks
journal, March 2018
- Cecen, Ahmet; Dai, Hanjun; Yabansu, Yuksel C.
- Acta Materialia, Vol. 146
Strong-contrast expansions and approximations for the effective conductivity of isotropic multiphase composites
journal, November 2003
- Pham, D. C.; Torquato, S.
- Journal of Applied Physics, Vol. 94, Issue 10
Computational homogenization of effective permeability in three-phase mesoscale concrete
journal, September 2016
- Li, Xinxin; Xu, Yi; Chen, Shenghong
- Construction and Building Materials, Vol. 121
Data science approaches for microstructure quantification and feature identification in porous membranes
journal, October 2017
- Altschuh, Patrick; Yabansu, Yuksel C.; Hötzer, Johannes
- Journal of Membrane Science, Vol. 540
Microstructure and property based statistically equivalent RVEs for intragranular microstructures of Ni-based superalloys
journal, September 2018
- Pinz, M.; Weber, G.; Lenthe, W. C.
- Acta Materialia, Vol. 157
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
Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting
journal, September 1988
- Cleveland, William S.; Devlin, Susan J.
- Journal of the American Statistical Association, Vol. 83, Issue 403
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides
journal, September 2020
- Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna
- Scientific Reports, Vol. 10, Issue 1
Applied Nonparametric Regression.
journal, January 1993
- Coshall, John; Hardle, Wolfgang
- The Statistician, Vol. 42, Issue 2
Design and analysis of computer experiments
conference, September 1998
- Booker, Andrew
- 7th AIAA/USAF/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization
Design and analysis of computer experiments
journal, December 2010
- Kuhnt, Sonja; Steinberg, David M.
- AStA Advances in Statistical Analysis, Vol. 94, Issue 4
Local Gaussian Process Approximation for Large Computer Experiments
text, January 2015
- Gramacy, Robert B.; Apley, Daniel W.
- Taylor & Francis
Local Gaussian process approximation for large computer experiments
text, January 2015
- Gramacy, Robert B.; Apley, Daniel W.
- Taylor & Francis
BART: Bayesian additive regression trees
text, January 2008
- Chipman, Hugh A.; George, Edward I.; McCulloch, Robert E.
- arXiv
Composite Gaussian process models for emulating expensive functions
text, January 2013
- Ba, Shan; Joseph, V. Roshan
- arXiv
Convolutional neural networks for atomistic systems
text, January 2017
- Ryczko, Kevin; Mills, Kyle; Luchak, Iryna
- arXiv
Applied Machine Learning to Predict Stress Hotspots I: Face Centered Cubic Materials
preprint, January 2017
- Mangal, Ankita; Holm, Elizabeth A.
- arXiv
Works referencing / citing this record:
Application of Gaussian process autoregressive models for capturing the time evolution of microstructure statistics from phase-field simulations for sintering of polycrystalline ceramics
journal, September 2019
- Yabansu, Yuksel C.; Rehn, Veronika; Hötzer, Johannes
- Modelling and Simulation in Materials Science and Engineering, Vol. 27, Issue 8