Gaussian process regression and conditional polynomial chaos for parameter estimation

DOI10.1016/J.JCP.2020.109520zbMATH Open1437.62334arXiv1908.00424OpenAlexW3022916086MaRDI QIDQ781985FDOQ781985

D. Kharzeev

Publication date: 21 July 2020

Published in: Journal of Computational Physics (Search for Journal in Brave)

Abstract: We present a new approach for constructing a data-driven surrogate model and using it for Bayesian parameter estimation in partial differential equation (PDE) models. We first use parameter observations and Gaussian Process regression to condition the Karhunen-Lo'{e}ve (KL) expansion of the unknown space-dependent parameters and then build the conditional generalized Polynomial Chaos (gPC) surrogate model of the PDE states. Next, we estimate the unknown parameters by computing coefficients in the KL expansion minimizing the square difference between the gPC predictions and measurements of the states using the Markov Chain Monte Carlo method. Our approach addresses two major challenges in the Bayesian parameter estimation. First, it reduces dimensionality of the parameter space and replaces expensive direct solutions of PDEs with the conditional gPC surrogates. Second, the estimated parameter field exactly matches the parameter measurements. In addition, we show that the conditional gPC surrogate can be used to estimate the states variance, which, in turn, can be used to guide data acquisition. We demonstrate that our approach improves its accuracy with application to one- and two-dimensional Darcy equation with (unknown) space-dependent hydraulic conductivity. We also discuss the effect of hydraulic conductivity and head locations on the accuracy of the hydraulic conductivity estimations.

Full work available at URL: https://arxiv.org/abs/1908.00424

zbMATH Keywords

Markov chain Monte Carlo methodKL expansionconditional Gaussian process regressionconditional gPC surrogate

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Monte Carlo methods (65C05) Gaussian processes (60G15)

Cites Work

• Bayesian experimental design: A review
• Title not available (Why is that?)
• The multivariate normal distribution
• Title not available (Why is that?)
• Inverse problems: a Bayesian perspective
• Title not available (Why is that?)
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Karhunen-Loève approximation of random fields by generalized fast multipole methods
• A regularizing Levenberg - Marquardt scheme, with applications to inverse groundwater filtration problems
• Title not available (Why is that?)
• A Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data
• Title not available (Why is that?)
• High-Order Collocation Methods for Differential Equations with Random Inputs
• An adaptive hierarchical sparse grid collocation algorithm for the solution of stochastic differential equations
• STOCHASTIC COLLOCATION ALGORITHMS USING l1-MINIMIZATION
• Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
• Title not available (Why is that?)
• Non-intrusive low-rank separated approximation of high-dimensional stochastic models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Reweighted \(\ell_1\) minimization method for stochastic elliptic differential equations
• Compressive sampling of polynomial chaos expansions: convergence analysis and sampling strategies
• Stochastic spectral methods for efficient Bayesian solution of inverse problems
• A Family of Trust-Region-Based Algorithms for Unconstrained Minimization with Strong Global Convergence Properties
• Data-driven model reduction for the Bayesian solution of inverse problems
• A Least-Squares Method for Sparse Low Rank Approximation of Multivariate Functions
• Numerical methods for experimental design of large-scale linear ill-posed inverse problems
• Gradient-based optimization for regression in the functional tensor-train format
• Conditional stochastic simulations of flow and transport with Karhunen-Loève expansions, stochastic collocation, and sequential Gaussian simulation
• Adaptive Sparse Grid Model Order Reduction for Fast Bayesian Estimation and Inversion
• A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems
• Conditional Simulation of Flow in Heterogeneous Porous Media with the Probabilistic Collocation Method

Cited In (11)

• A Gaussian Process Regression Model for Distribution Inputs
• Physics-informed Karhunen-Loéve and neural network approximations for solving inverse differential equation problems
• Title not available (Why is that?)
• Multi-fidelity Gaussian process regression for prediction of random fields
• Physics-informed machine learning method with space-time Karhunen-Loève expansions for forward and inverse partial differential equations
• Randomized physics-informed machine learning for uncertainty quantification in high-dimensional inverse problems
• Title not available (Why is that?)
• On the construction of uncertain time series surrogates using polynomial chaos and Gaussian processes
• Nested polynomial trends for the improvement of Gaussian process-based predictors
• Properties of the Bayesian parameter estimation of a regression based on Gaussian processes
• A gaussian process with parabolic covariances

Uses Software

• Matlab
• DREAM

This page was built for publication: Gaussian process regression and conditional polynomial chaos for parameter estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q781985)