×

Kernel principal component analysis for stochastic input model generation. (English) Zbl 1252.65014

Summary: The stochastic analysis of random heterogeneous media provides useful information only if realistic input models of the material property variations are used. These input models are often constructed from a set of experimental samples of the underlying random field. To this end, the Karhunen-Loève expansion, also known as principal component analysis (PCA), is the most popular model reduction method due to its uniform mean-square convergence. However, it only projects the samples onto an optimal linear subspace, which results in an unreasonable representation of the original data if they are non-linearly related to each other. In other words, it only preserves the first-order (mean) and second-order statistics (covariance) of a random field, which is insufficient for reproducing complex structures.
This paper applies kernel principal component analysis (KPCA) to construct a reduced-order stochastic input model for the material property variation in heterogeneous media. KPCA can be considered as a nonlinear version of PCA. Through the use of kernel functions, KPCA further enables the preservation of higher-order statistics of the random field, instead of just two-point statistics as in the standard Karhunen-Loève expansion. Thus, this method can model non-Gaussian, non-stationary random fields. In this work, we also propose a new approach to solve the pre-image problem involved in KPCA. In addition, polynomial chaos (PC) expansion is used to represent the random coefficients in KPCA which provides a parametric stochastic input model. Thus, realizations, which are statistically consistent with the experimental data, can be generated in an efficient way. We illustrate the methodology by constructing a low-dimensional stochastic input model to represent channelized permeability in porous media.

MSC:

65C30 Numerical solutions to stochastic differential and integral equations
60H15 Stochastic partial differential equations (aspects of stochastic analysis)
60H35 Computational methods for stochastic equations (aspects of stochastic analysis)
35R60 PDEs with randomness, stochastic partial differential equations
60G60 Random fields
62H25 Factor analysis and principal components; correspondence analysis
76S05 Flows in porous media; filtration; seepage
76M35 Stochastic analysis applied to problems in fluid mechanics

Software:

sm
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Zhang, D., Stochastic Method for Flow in Porous Media: Coping with Uncertainties (2002), Academic Press: Academic Press San Diego
[2] Zhang, D.; Lu, Z., An efficient, high-order perturbation approach for flow in random porous media via Karhunen-Loève and polynomial expansions, Journal of Computational Physics, 194, 773-794 (2004) · Zbl 1101.76048
[3] Ghanem, R.; Spanos, P. D., Stochastic Finite Elements: A Spectral Approach (1991), Springer-Verlag: Springer-Verlag New York · Zbl 0722.73080
[4] Xiu, D.; Karniadakis, G. E., The Wiener-Askey polynomial chaos for stochastic differential equations, SIAM Journal on Scientific Computing, 24, 619-644 (2002) · Zbl 1014.65004
[5] Xiu, D.; Karniadakis, G. E., Modeling uncertainty in flow simulations via generalized polynomial chaos, Journal of Computational Physics, 187, 137-167 (2003) · Zbl 1047.76111
[6] Ma, X.; Zabaras, N., A stabilized stochastic finite element second-order projection method for modeling natural convection in random porous media, Journal of Computational Physics, 227, 8448-8471 (2008) · Zbl 1163.76029
[7] Babuška, I.; Nobile, F.; Tempone, R., A stochastic collocation method for elliptic partial differential equations with random input data, SIAM Journal on Numerical Analysis, 45, 1005-1034 (2007) · Zbl 1151.65008
[8] Xiu, D.; Hesthaven, J. S., High-order collocation methods for differential equations with random inputs, SIAM Journal on Scientific Computing, 27, 1118-1139 (2005) · Zbl 1091.65006
[9] Ganapathysubramanian, B.; Zabaras, N., Sparse grid collocation schemes for stochastic natural convection problems, Journal of Computational Physics, 225, 652-685 (2007) · Zbl 1343.76059
[10] Nobile, F.; Tempone, R.; Webster, C. G., A sparse grid stochastic collocation method for partial differential equations with random input data, SIAM Journal on Numerical Analysis, 46, 2309-2345 (2008) · Zbl 1176.65137
[11] Ma, X.; Zabaras, N., An adaptive hierarchical sparse grid collocation algorithm for the solution of stochastic differential equations, Journal of Computational Physics, 228, 3084-3113 (2009) · Zbl 1161.65006
[12] Ma, X.; Zabaras, N., An adaptive high-dimensional stochastic model representation technique for the solution of stochastic partial differential equations, Journal of Computational Physics, 229, 3884-3915 (2010) · Zbl 1189.65019
[13] Ma, X.; Zabaras, N., An efficient bayesian inference approach to inverse problems based on an adaptive sparse grid collocation method, Inverse Problems, 25, 035013 (2009) · Zbl 1161.62011
[14] Lin, G.; Tartakovsky, A., An efficient, high-order probabilistic collocation method on sparse grids for three-dimensional flow and solute transport in randomly heterogeneous porous media, Advances in Water Resources, 32, 712-722 (2009)
[15] Loève, M., Probability Theory (1977), Springer-Verlag: Springer-Verlag Berlin · Zbl 0359.60001
[16] Jolliffe, I. T., Principal Component Analysis (2002), Springer-Verlag: Springer-Verlag New York · Zbl 1011.62064
[17] Desceliers, C.; Ghanem, R.; Soize, C., Maximum likelihood estimation of stochastic chaos representations from experimental data, International Journal for Numerical Methods in Engineering, 66, 978-1001 (2006) · Zbl 1110.74826
[18] Ghanem, R. G.; Doostan, A., On the construction and analysis of stochastic models: characterization and propagation of the errors associated with limited data, Journal of Computational Physics, 217, 63-81 (2006) · Zbl 1102.65004
[19] Das, S.; Ghanem, R.; Spall, J. C., Asymptotic sampling distribution for polynomial chaos representation from data: a maximum entropy and fisher information approach, SIAM Journal on Scientific Computing, 30, 2207-2234 (2008) · Zbl 1181.62004
[20] Das, S.; Ghanem, R.; Finette, S., Polynomial chaos representation of spatio-temporal random fields from experimental measurements, Journal of Computational Physics, 228, 8726-8751 (2009) · Zbl 1177.65019
[21] Stefanou, G.; Nouy, A.; Clement, A., Identification of random shapes from images through polynomial chaos expansion of random level set functions, International Journal for Numerical Methods in Engineering, 79, 127-155 (2009) · Zbl 1171.74449
[22] Arnst, M.; Ghanem, R.; Soize, C., Identification of Bayesian posteriors for coefficients of chaos expansions, Journal of Computational Physics, 229, 3134-3154 (2010) · Zbl 1184.62034
[23] Soize, C., Identification of high-dimension polynomial chaos expansions with random coefficients for non-gaussian tensor-valued random fields using partial and limited experimental data, Computer Methods in Applied Mechanics and Engineering, 199, 2150-2164 (2010) · Zbl 1231.74501
[24] Rosenblatt, M., Remarks on a multivariate transformation, Ann. Math. Statist., 23, 470-472 (1952) · Zbl 0047.13104
[25] Sargsyan, K.; Debusschere, B.; Najm, H.; Maître, O. L., Spectral representation and reduced order modeling of the dynamics of stochastic reaction networks via adaptive data partitioning, SIAM Journal on Scientific Computing, 31, 4395-4421 (2010) · Zbl 1206.60043
[26] Babuška, I.; Liu, K.-M.; Tempone, R., Solving stochastic partial differential equations based on the experimental data, Mathematical Models and Methods in Applied Sciences, 13, 415-444 (2003) · Zbl 1052.60047
[27] Ganapathysubramanian, B.; Zabaras, N., Modeling diffusion in random heterogeneous media: data-driven models, stochastic collocation and the variational multiscale method, Journal of Computational Physics, 226, 326-353 (2007) · Zbl 1124.65007
[28] Agarwal, N.; Aluru, N. R., A data-driven stochastic collocation approach for uncertainty quantification in mems, International Journal for Numerical Methods in Engineering, 83, 575-597 (2010) · Zbl 1197.74197
[29] Ganapathysubramanian, B.; Zabaras, N., A non-linear dimension reduction methodology for generating data-driven stochastic input models, Journal of Computational Physics, 227, 6612-6637 (2008) · Zbl 1141.82316
[30] Tenenbaum, J. B.; Silva, V.d.; Langford, J. C., A global geometric framework for nonlinear dimensionality reduction, Science, 290, 2319-2323 (2000)
[31] Schlkopf, B.; Smola, A.; Muller, K.-R., Nonlinear component analysis as a kernel eigenvalue problem, Neural Computation, 10, 1299-1319 (1998)
[32] Schlkopf, B.; Smola, A., Learning with Kernels (2002), MIT Press
[33] Shawe-Taylor, J.; Cristianini, N., Kernel Methods for Pattern Analysis (2004), Cambridge University Press
[34] Mika, S.; Bernhard, S.; Alexander, S.; Klaus-Robert, M.; Scholz, M.; Ratsch, G., Kernel PCA and de-noising in feature spaces, (Advances in Neural Information Processing Systems, vol. 11 (1999), MIT Press), 536-542
[35] Y. Rathi, S. Dambreville, A. Tannenbaum, Statistical shape analysis using kernel PCA, in: Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, SPIE, 2006, p. 60641B.; Y. Rathi, S. Dambreville, A. Tannenbaum, Statistical shape analysis using kernel PCA, in: Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, SPIE, 2006, p. 60641B.
[36] Sarma, P.; Durlofsky, L. J.; Aziz, K., Kernel principal component analysis for efficient, differentiable parameterization of multipoint geostatistics, Mathematical Geosciences, 40, 3-32 (2008) · Zbl 1144.86004
[37] Scheidt, C.; Caers, J., Representing spatial uncertainty using distances and kernels, Mathematical Geosciences, 41, 397-419 (2009) · Zbl 1163.86317
[38] Kwok, J.-Y.; Tsang, I.-H., The pre-image problem in kernel methods, IEEE Transactions on Neural Networks, 15, 1517-1525 (2004)
[39] Venturi, D., A fully symmetric nonlinear biorthogonal decomposition theory for random fields, Physica D, 240, 4-5, 415-425 (2011) · Zbl 1209.60031
[40] Ravindran, S. S., A reduced-order approach for optimal control of fluids using proper orthogonal decomposition, International Journal for Numerical Methods in Fluids, 34, 425-448 (2000) · Zbl 1005.76020
[41] Bowman, A. W.; Azzalini, A., Applied Smoothing Techniques for Data Analysis: The Kernel Approach with S-Plust Illustrations (1997), Oxford University Press · Zbl 0889.62027
[42] Williams, C. K., On a connection between kernel PCA and metric multidimensional scaling, Machine Learning, 46, 11-19 (2002) · Zbl 1052.68118
[43] Strebelle, S., Conditional simulation of complex geological structures using multiple-point statistics, Mathematical Geology, 34, 1-21 (2002) · Zbl 1036.86013
[44] Ma, X.; Zabaras, N., A stochastic mixed finite element heterogeneous multiscale method for flow in porous media, Journal of Computational Physics, 230, 4696-4722 (2011) · Zbl 1416.76119
[45] Suzuki, S.; Caers, J., A distance-based prior model parameterization for constraining solutions of spatial inverse problems, Mathematical Geosciences, 40, 445-469 (2008) · Zbl 1142.86304
[46] Torquato, S., Random Heterogeneous Materials: Microstructure and Macroscopic Properties (2002), Springer-Verlag: Springer-Verlag New York · Zbl 0988.74001
[47] Venturi, D.; Wan, X.; Karniadakis, G. E., Stochastic low-dimensional modelling of a random laminar wake past a circular cylinder, Journal of Fluid Mechanics, 606, 339-367 (2008) · Zbl 1146.76018
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.