Kernel Principal Component Analysis for Efficient, Differentiable Parameterization of Multipoint Geostatistics

Abstract This paper describes a novel approach for creating an efficient, general, and differentiable parameterization of large-scale non-Gaussian, non-stationary random fields (represented by multipoint geostatistics) that is capable of reproducing complex geological structures such as channels. Such parameterizations are appropriate for use with gradient-based algorithms applied to, for example, history-matching or uncertainty propagation. It is known that the standard Karhunen–Loeve (K–L) expansion, also called linear principal component analysis or PCA, can be used as a differentiable parameterization of input random fields defining the geological model. The standard K–L model is, however, limited in two respects. It requires an eigen-decomposition of the covariance matrix of the random field, which is prohibitively expensive for large models. In addition, it preserves only the two-point statistics of a random field, which is insufficient for reproducing complex structures. In this work, kernel PCA is applied to address the limitations associated with the standard K–L expansion. Although widely used in machine learning applications, it does not appear to have found any application for geological model parameterization. With kernel PCA, an eigen-decomposition of a small matrix called the kernel matrix is performed instead of the full covariance matrix. The method is much more efficient than the standard K–L procedure. Through use of higher order polynomial kernels, which implicitly define a high-dimensionality feature space, kernel PCA further enables the preservation of high-order statistics of the random field, instead of just two-point statistics as in the K–L method. The kernel PCA eigen-decomposition proceeds using a set of realizations created by geostatistical simulation (honoring two-point or multipoint statistics) rather than the analytical covariance function. We demonstrate that kernel PCA is capable of generating differentiable parameterizations that reproduce the essential features of complex geological structures represented by multipoint geostatistics. The kernel PCA representation is then applied to history match a water flooding problem. This example demonstrates that kernel PCA can be used with gradient-based history matching to provide models that match production history while maintaining multipoint geostatistics consistent with the underlying training image.

[1]  P. C. Shah,et al.  Reservoir History Matching by Bayesian Estimation , 1976 .

[2]  Gene H. Golub,et al.  Matrix computations , 1983 .

[3]  C. W. Harper,et al.  A FORTRAN IV program for comparing ranking algorithms in quantitative biostratigraphy , 1984 .

[4]  P. Kitanidis Parameter Uncertainty in Estimation of Spatial Functions: Bayesian Analysis , 1986 .

[5]  L. Sirovich Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[6]  L. Sirovich Turbulence and the dynamics of coherent structures. III. Dynamics and scaling , 1987 .

[7]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Clayton V. Deutsch,et al.  GSLIB: Geostatistical Software Library and User's Guide , 1993 .

[9]  Dean S. Oliver,et al.  Multiple Realizations of the Permeability Field From Well Test Data , 1996 .

[10]  Dean S. Oliver,et al.  Conditioning Permeability Fields to Pressure Data , 1996 .

[11]  Dean S. Oliver,et al.  Reparameterization Techniques for Generating Reservoir Descriptions Conditioned to Variograms and Well-Test Pressure Data , 1996 .

[12]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[13]  Gunnar Rätsch,et al.  Kernel PCA pattern reconstruction via approximate pre-images. , 1998 .

[14]  Benoit Noetinger,et al.  Gradual Deformation and Iterative Calibration of Sequential Stochastic Simulations , 2001 .

[15]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[16]  Kok-Kwang Phoon,et al.  Convergence study of the truncated Karhunen–Loeve expansion for simulation of stochastic processes , 2001 .

[17]  A. Journel,et al.  Reservoir Modeling Using Multiple-Point Statistics , 2001 .

[18]  R. Ghanem,et al.  Polynomial chaos decomposition for the simulation of non-gaussian nonstationary stochastic processes , 2002 .

[19]  Sebastien Strebelle,et al.  Conditional Simulation of Complex Geological Structures Using Multiple-Point Statistics , 2002 .

[20]  Václav Hlaváč,et al.  Statistical Pattern Recognition Toolbox for Matlab User's guide , 2004 .

[21]  Jef Caers,et al.  Multiple-point Geostatistics: A Quantitative Vehicle for Integrating Geologic Analogs into Multiple Reservoir Models , 2004 .

[22]  Ivor W. Tsang,et al.  The pre-image problem in kernel methods , 2003, IEEE Transactions on Neural Networks.

[23]  Louis J. Durlofsky,et al.  Efficient Closed-loop Production Optimization Under Uncertainty , 2005 .

[24]  J. Jansen,et al.  Closed-loop reservoir management , 2005 .

[25]  L. Durlofsky,et al.  Efficient real-time reservoir management using adjoint-based optimal control and model updating , 2006 .

[26]  J. Caers,et al.  The Probability Perturbation Method: A New Look at Bayesian Inverse Modeling , 2006 .

[27]  Louis J. Durlofsky,et al.  A New Approach to Automatic History Matching Using Kernel PCA , 2007 .

[28]  Louis J. Durlofsky,et al.  Computational Techniques for Closed–loop Reservoir Modeling with Application to a Realistic Reservoir , 2008 .