Bayesian and variational Bayesian approaches for flows in heterogeneous random media
From MaRDI portal
Publication:1692018
DOI10.1016/J.JCP.2017.04.034zbMATH Open1378.76116arXiv1611.01213OpenAlexW2550769910MaRDI QIDQ1692018FDOQ1692018
Authors: Keren Yang, Nilabja Guha, Y. Efendiev, Bani Mallick 
Publication date: 26 January 2018
Published in: Journal of Computational Physics (Search for Journal in Brave)
Abstract: In this paper, we study porous media flows in heterogeneous stochastic media. We propose an efficient forward simulation technique that is tailored for variational Bayesian inversion. As a starting point, the proposed forward simulation technique decomposes the solution into the sum of separable functions (with respect to randomness and the space), where each term is calculated based on a variational approach. This is similar to Proper Generalized Decomposition (PGD). Next, we apply a multiscale technique to solve for each term and, further, decompose the random function into 1D fields. As a result, our proposed method provides an approximation hierarchy for the solution as we increase the number of terms in the expansion and, also, increase the spatial resolution of each term. We use the hierarchical solution distributions in a variational Bayesian approximation to perform uncertainty quantification in the inverse problem. We conduct a detailed numerical study to explore the performance of the proposed uncertainty quantification technique and show the theoretical posterior concentration.
Full work available at URL: https://arxiv.org/abs/1611.01213
Recommendations
- Multilevel approximate Bayesian approaches for flows in highly heterogeneous porous media and their applications
- Multiscale finite element methods for stochastic porous media flow equations and application to uncertainty quantification
- A nonparametric belief propagation method for uncertainty quantification with applications to flow in random porous media
- Conditional simulation of flow in heterogeneous porous media with the probabilistic collocation method
- Uncertainty propagation using infinite mixture of gaussian processes and variational Bayesian inference
Inference from spatial processes (62M30) PDEs in connection with fluid mechanics (35Q35) Inverse problems for PDEs (35R30) Flows in porous media; filtration; seepage (76S05) Variational methods applied to problems in fluid mechanics (76M30)
Cites Work
- Statistical and computational inverse problems.
- Parameter Estimation of Partial Differential Equation Models
- Convergence rates of posterior distributions.
- Statistical inverse problems: discretization, model reduction and inverse crimes
- Inverse problems: a Bayesian perspective
- Introduction to Bayesian Scientific Computing
- Bayesian nonparametrics
- Posterior consistency of logistic Gaussian process priors in density estimation
- Generalized multiscale finite element methods (GMsFEM)
- Inverse Problem Theory and Methods for Model Parameter Estimation
- A new family of solvers for some classes of multidimensional partial differential equations encountered in kinetic theory modelling of complex fluids. II: Transient simulation using space-time separated representations
- Results and questions on a nonlinear approximation approach for solving high-dimensional partial differential equations
- A new family of solvers for some classes of multidimensional partial differential equations encountered in kinetic theory modeling of complex fluids
- Hierarchical Bayesian inference for ill-posed problems via variational method
- Multilevel Markov Chain Monte Carlo Method for High-Contrast Single-Phase Flow Problems
- Well-posed Bayesian geometric inverse problems arising in subsurface flow
- Application of the generalized multiscale finite element method in parameter-dependent PDE simulations with a variable-separation technique
- Adaptive multiscale model reduction with generalized multiscale finite element methods
- A variational Bayesian approach for inverse problems with skew-\(t\) error distributions
Cited In (18)
- VI-DGP: a variational inference method with deep generative prior for solving high-dimensional inverse problems
- Variational Bayes' Method for Functions with Applications to Some Inverse Problems
- A Bayesian framework for the validation of models for subsurface flows: synthetic experiments
- A prefetching technique for prediction of porous media flows
- An efficient algorithm for a class of stochastic forward and inverse Maxwell models in \(\mathbb{R}^3\)
- Flowgraph models: a Bayesian case study in construction engineering
- Variational inference at glacier scale
- Randomized reduced forward models for efficient Metropolis-Hastings MCMC, with application to subsurface fluid flow and capacitance tomography
- Toward an enhanced Bayesian estimation framework for multiphase flow soft-sensing
- Gibbs Flow for Approximate Transport with Applications to Bayesian Computation
- Uncertainty propagation using infinite mixture of gaussian processes and variational Bayesian inference
- Bayesian decision making using partial data for fractured poroelastic media
- A Bayesian Approach to Estimating Background Flows from a Passive Scalar
- A nonparametric belief propagation method for uncertainty quantification with applications to flow in random porous media
- Multilevel approximate Bayesian approaches for flows in highly heterogeneous porous media and their applications
- Dynamic data-driven Bayesian GMsFEM
- A Gaussian Process Emulator Based Approach for Bayesian Calibration of a Functional Input
- Approximate Bayesian model inversion for PDEs with heterogeneous and state-dependent coefficients
This page was built for publication: Bayesian and variational Bayesian approaches for flows in heterogeneous random media
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1692018)
