Abstract
Quantitative treatment of microstructure data is the first step in establishing the structure–property linkages using materials informatics. However, the microstructure data are often huge and require dimensionality reduction techniques to use it in a computationally meaningful way. In this paper, we present a simple and unique approach to estimate the intrinsic dimensionality of microstructure data. By using principal component analysis (PCA) and multi-dimensional scaling (MDS), we demonstrate the effects of global and local metrics on various classes of 2D and 3D synthetic two-phase microstructure data on the intrinsic dimensionality (ID). Further, we establish the influence of the phase fraction and the inherent stochastic nature of the microstructure on ID estimation. It is observed that 2-point spatial correlation statistics greatly influence intrinsic dimensionality. A change in the intrinsic dimensionality is observed with an increase in the volume fraction of the phase. Considerable variation is observed in metric values for MDS compared to PCA, with an increase in dimensions. We also provide a reduced-order phase fraction benchmark of intrinsic dimensionality (ID) for high dimensional microstructure data. The presented framework is based on a simple and effective trade-off between property preservation and complexity reduction.
Similar content being viewed by others
Notes
Stress referred here is not to be confused with mechanical stress.
References
Fullwood DT, Niezgoda SR, Adams BL, Kalidindi SR (2010) Microstructure sensitive design for performance optimization. Progress Mater Sci 55(6):477
Bostanabad R, Zhang Y, Li X, Kearney T, Brinson LC, Apley DW, Liu WK, Chen W (2018) Computational microstructure characterization and reconstruction: review of the state-of-the-art techniques. Prog Mater Sci 95:1
Lebensohn R, Rollett A (2020) Spectral methods for full-field micromechanical modelling of polycrystalline materials. Comput Mater Sci 173:109336
Lebensohn R, Castañeda P, Brenner R, Castelnau O (2011) Full-field vs. homogenization methods to predict microstructure–property relations for polycrystalline materials. In: Computational methods for microstructure–property relationships, pp 393–441
Kanjarla A, Lebensohn R, Balogh L, Tomé C (2012) Study of internal lattice strain distributions in stainless steel using a full-field elasto-viscoplastic formulation based on fast Fourier transforms. Acta Mater 60(6):3094
Qidwai SM, Turner DM, Niezgoda SR, Lewis AC, Geltmacher AB, Rowenhorst DJ, Kalidindi SR (2012) Estimating the response of polycrystalline materials using sets of weighted statistical volume elements. Acta Mater 60(13):5284
Pokharel R, Lind J, Kanjarla AK, Lebensohn RA, Li SF, Kenesei P, Suter RM, Rollett AD (2014) Polycrystal plasticity: comparison between grain - scale observations of deformation and simulations. Annual Rev Condens Matter Phys 5(1):317
Pinz M, Weber G, Ghosh S (2019) Generating 3d virtual microstructures and statistically equivalent RVES for subgranular gamma-gamma’ microstructures of nickel-based superalloys. Comput Mater Sci 167:198
Yuan X, Ren D, Wang Z, Guo C (2013) Dimension projection matrix/tree: interactive subspace visual exploration and analysis of high dimensional data. IEEE Trans Vis Comput Gr 19(12):2625
Niezgoda SR, Kanjarla AK, Kalidindi SR (2013) Novel microstructure quantification framework for databasing, visualization, and analysis of microstructure data. Integr Mater Manuf Innov 2(1):54
Niezgoda SR, Yabansu YC, Kalidindi SR (2011) Understanding and visualizing microstructure and microstructure variance as a stochastic process. Acta Mater 59(16):6387
Fullwood DT, Niezgoda SR, Kalidindi SR (2008) Microstructure reconstructions from 2-point statistics using phase-recovery algorithms. Acta Mater 56(5):942
Kalidindi SR, Niezgoda SR, Salem AA (2011) Microstructure informatics using higher-order statistics and efficient data-mining protocols. JOM 63(4):34
Niezgoda S, Fullwood D, Kalidindi S (2008) Delineation of the space of 2-point correlations in a composite material system. Acta Mater 56(18):5285
Li Z, Wen B, Zabaras N (2010) Computing mechanical response variability of polycrystalline microstructures through dimensionality reduction techniques. Comput Mater Sci 49(3):568
Jung J, Yoon JI, Park HK, Kim JY, Kim HS (2019) An efficient machine learning approach to establish structure–property linkages. Comput Mater Sci 156:17
Kruskal JB (1964) Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 29(1):1
Samudrala S, Rajan K, Ganapathysubramanian B (2013) Informatics for materials science and engineering. Elsevier, Amsterdam, pp 97–119
Cang R, Xu Y, Chen S, Liu Y, Jiao Y, Yi Ren M (2017) Microstructure representation and reconstruction of heterogeneous materials via deep belief network for computational material design. J Mech Des 139(7)
Fukunaga K (2013) Introduction to statistical pattern recognition. Elsevier, Amsterdam
Van Der Maaten LJP, Postma EO, Van Den Herik HJ (2009) Dimensionality reduction: a comparative review. J Mach Learn Res 10:1
Camastra F (2003) Data dimensionality estimation methods: a survey. Pattern Recogn 36:2945
Campadelli P, Casiraghi E, Ceruti C, Rozza A (2015) Intrinsic dimension estimation: relevant techniques and a benchmark framework. Math Problems Eng 2015:1
Gracia A, González S, Robles V, Menasalvas E (2014) A methodology to compare dimensionality reduction algorithms in terms of loss of quality. Inf Sci 270:1
Hyman JD, Winter LC (2014) Stochastic generation of explicit pore structures by thresholding Gaussian random fields. J Comput Phys 277:16
The Mathworks, Inc., (2018) Natick, Massachusetts, MATLAB version 9.5.0.1298439 (R2018b) Update 7
Cecen A, Fast T, Kalidindi SR (2016) Versatile algorithms for the computation of 2-point spatial correlations in quantifying material structure. Integr Mater Manuf Innov 5(1):1
Cecen A, Kalidindi SR (2015) Matlab spatial correlation toolbox: eelease 3:1
Mohd Aris KD, Mustapha F, Salit MS, Majid AA (2014) Condition structural index using principal component analysis for undamaged, damage and repair conditions of carbon fiber-reinforced plastic laminate. J Intell Mater Syst Struct 25(5):575
Agrawal A, Deshpande PD, Cecen A, Basavarsu GP, Choudhary AN, Kalidindi SR (2014) Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters. Integr Mater Manuf Innov 3(1):8
Rajan K, Suh C, Mendez PF (2009) Principal component analysis and dimensional analysis as materials informatics tools to reduce dimensionality in materials science and engineering. Stat Anal Data Min ASA Data Sci J 1(6):361
Shenai PM, Xu Z, Zhao Y (2012) Principal component analysis-engineering applications. IntechOpen, pp 25–40
Cox MA, Cox TF (2008) Handbook of data visualization. Springer, New York, pp 315–347
Thorndike RL (1953) Who belongs in the family? Psychometrika 18:267
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825
Lee JA, Verleysen M (2009) Quality assessment of dimensionality reduction: rank-based criteria. Neurocomputing 72(7–9):1431
Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer, New York
Sumithra V, Surendran S (2015) A review of various linear and non linear dimensionality reduction techniques. Int J Comput Sci Inf Technol 6:2354
van Wezel MC, Kosters WA (2004) Nonmetric multidimensional scaling: neural networks versus traditional techniques. Intell Data Anal 8(6):601
Borg I, Groenen PJ (2005) Modern multidimensional scaling: theory and applications. Springer, New York
Lubbers N, Lookman T, Barros K (2017) Inferring low-dimensional microstructure representations using convolutional neural networks. Phys Rev E 96(5):052111
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2832
De Leeuw J, Mair P (2011) Multidimensional scaling using majorization: SMACOF in R. https://escholarship.org/uc/item/9z64v481
Siegel S, Castellan N (1988) Nonparametric statistics for the behavioral sciences. McGraw-Hill international editions statistics series. McGraw-Hill
Venna J, Kaski S (2006) Local multidimensional scaling. Neural Netw 19:889
Chen L, Buja A (2009) Local multidimensional scaling for nonlinear dimension reduction, graph drawing, and proximity analysis. J Am Stat Assoc 104(485):209
Tenenbaum J, Silva V, Langford J (2012) Geometric structure of high-dimensional data and dimensionality reduction. Science 290(December):151
Handa H (2011) On the effect of dimensionality reduction by manifold learning for evolutionary learning. Evol Syst 2:235
Sammon JW (1969) A nonlinear mapping for data structure analysis. IEEE Trans Comput C 18(5):401
Latypov M, Kalidindi S (2017) Data-driven reduced order models for effective yield strength and partitioning of strain in multiphase materials. J Comput Phys 346:242–261
Acknowledgements
Sanket Thakre gratefully acknowledges the support from the Prime Minister’s Research Fellowship (PMRF) awarded by the Ministry of Human Resource Development, India. The comments from anonymous referee were helpful in improving the manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Thakre, S., Harshith, V. & Kanjarla, A.K. Intrinsic Dimensionality of Microstructure Data. Integr Mater Manuf Innov 10, 44–57 (2021). https://doi.org/10.1007/s40192-021-00200-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40192-021-00200-z