Regression-based sparse polynomial chaos for uncertainty quantification of subsurface flow models

Abstract

Surrogate-modelling techniques including Polynomial Chaos Expansion (PCE) is commonly used for statistical estimation (aka. Uncertainty Quantification) of quantities of interests obtained from expensive computational models. PCE is a data-driven regression-based technique that relies on spectral polynomials as basis-functions. In this technique, the outputs of few numerical simulations are used to estimate the PCE coefficients within a regression framework combined with regularization techniques where the regularization parameters are estimated using standard cross-validation as applied in supervised machine learning methods. In the present work, we introduce an efficient method for estimating the PCE coefficients combining Elastic Net regularization with a data-driven feature ranking approach. Our goal is to increase the probability of identifying the most significant PCE components by assigning each of the PCE coefficients a numerical value reflecting the magnitude of the coefficient and its stability with respect to perturbations in the input data. In our evaluations, the proposed approach has shown high convergence rate for high-dimensional problems, where standard feature ranking might be challenging due to the curse of dimensionality. The presented method is implemented within a standard machine learning library (Scikit-learn) allowing for easy experimentation with various solvers and regularization techniques (e.g. Tikhonov, LASSO, LARS, Elastic Net) and enabling automatic cross-validation techniques using a widely used and well tested implementation. We present a set of numerical tests on standard analytical functions, a two-phase subsurface flow model and a simulation dataset for CO2 sequestration in a saline aquifer. For all test cases, the proposed approach resulted in a significant increase in PCE convergence rates.

28 pages, 7 figures, published in Journal of Computational Physics (2019)

References in corpus (22)

• Scikit-learn: Machine Learning in Python
• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Rejoinder to "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
• Data-driven polynomial chaos expansion for machine learning regression
• Coherence Motivated Sampling and Convergence Analysis of Least-Squares Polynomial Chaos Regression
• Polynomial meta-models with canonical low-rank approximations: numerical insights and comparison to sparse polynomial chaos expansions
• Conservative model reduction for finite-volume models
• A machine learning approach for efficient uncertainty quantification using multiscale methods
• Enhancing Sparsity of Hermite Polynomial Expansions by Iterative Rotations
• Basis Adaptive Sample Efficient Polynomial Chaos (BASE-PC)
• A gradient enhanced ${\ell }_1$-minimization for sparse approximation of polynomial chaos expansions
• Data-driven polynomial chaos expansions: a weighted least-square approximation
• A preconditioning approach for improved estimation of sparse polynomial chaos expansions

Cited by in corpus (5)

• Sparse Polynomial Chaos Expansions: Literature Survey and Benchmark
• Uncertainty Quantification and Propagation in Surrogate-based Bayesian Inference
• Optimal Bayesian experimental design for subsurface flow problems
• A fully Bayesian sparse polynomial chaos expansion approach with joint priors on the coefficients and global selection of terms
• Physically interpretable machine learning algorithm on multidimensional non-linear fields