Regression-based sparse polynomial chaos for uncertainty quantification of subsurface flow models
From MaRDI portal
Publication:2222601
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.
Recommendations
- Data-driven polynomial chaos expansion for machine learning regression
- Sparse polynomial chaos expansions: literature survey and benchmark
- A robust and efficient stepwise regression method for building sparse polynomial chaos expansions
- PLS-based adaptation for efficient PCE representation in high dimensions
- Sparse polynomial chaos expansions using variational relevance vector machines
Cites work
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- A Hierarchical Multilevel Markov Chain Monte Carlo Algorithm with Applications to Uncertainty Quantification in Subsurface Flow
- A gradient enhanced \(\ell_{1}\)-minimization for sparse approximation of polynomial chaos expansions
- A machine learning approach for efficient uncertainty quantification using multiscale methods
- A near-optimal sampling strategy for sparse recovery of polynomial chaos expansions
- A new non-intrusive polynomial chaos using higher order sensitivities
- A robust and efficient stepwise regression method for building sparse polynomial chaos expansions
- A stochastic mixed finite element heterogeneous multiscale method for flow in porous media
- Adaptive sparse polynomial chaos expansion based on least angle regression
- Analysis of Data From Viral DNA Microchips
- Basis adaptive sample efficient polynomial chaos (BASE-PC)
- Blind Separation of Image Sources via Adaptive Dictionary Learning
- Coherence motivated sampling and convergence analysis of least squares polynomial chaos regression
- Conservative model reduction for finite-volume models
- Data-driven polynomial chaos expansions: a weighted least-square approximation
- Elastic-net regularization in learning theory
- Enhancing sparsity of Hermite polynomial expansions by iterative rotations
- Improving adaptive generalized polynomial chaos method to solve nonlinear random differential equations by the random variable transformation technique
- Kernel principal component analysis for stochastic input model generation
- Least angle regression. (With discussion)
- Multiscale model reduction for fluid infiltration simulation through dual-continuum porous media with localized uncertainties
- Nonlocal multicontinua upscaling for multicontinua flow problems in fractured porous media
- On Projection Matrix Optimization for Compressive Sensing Systems
- Polynomial meta-models with canonical low-rank approximations: numerical insights and comparison to sparse polynomial chaos expansions
- Post-injection trapping of mobile \(\text{CO}_{2}\) in deep aquifers: assessing the importance of model and parameter uncertainties
- Remarks on a Multivariate Transformation
- Robust optimization of subsurface flow using polynomial chaos and response surface surrogates
- Scikit-learn: machine learning in Python
- Stochastic collocation algorithms using \(\ell_1\)-minimization
- Uncertainty propagation of p-boxes using sparse polynomial chaos expansions
Cited in
(10)- Sparse polynomial chaos expansions: literature survey and benchmark
- Physically interpretable machine learning algorithm on multidimensional non-linear fields
- Special issue: advanced numerical modeling and algorithms for multiphase flow and transport
- Data-driven polynomial chaos expansion for machine learning regression
- A generalized multi-fidelity simulation method using sparse polynomial chaos expansion
- A fully Bayesian sparse polynomial chaos expansion approach with joint priors on the coefficients and global selection of terms
- Optimal Bayesian experimental design for subsurface flow problems
- Towards Practical Large-Scale Randomized Iterative Least Squares Solvers through Uncertainty Quantification
- Prior model identification during subsurface flow data integration with adaptive sparse representation techniques
- Gaussian process regression and conditional polynomial chaos for parameter estimation
This page was built for publication: Regression-based sparse polynomial chaos for uncertainty quantification of subsurface flow models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2222601)
