Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
arXiv:2102.03169 · doi:10.1016/j.jcp.2022.111008
Abstract
Estimation of spatially-varying parameters for computationally expensive forward models governed by partial differential equations is addressed. A novel multiscale Bayesian inference approach is introduced based on deep probabilistic generative models. Such generative models provide a flexible representation by inferring on each scale a low-dimensional latent encoding while allowing hierarchical parameter generation from coarse- to fine-scales. Combining the multiscale generative model with Markov Chain Monte Carlo (MCMC), inference across scales is achieved enabling us to efficiently obtain posterior parameter samples at various scales. The estimation of coarse-scale parameters using a low-dimensional latent embedding captures global and notable parameter features using an inexpensive but inaccurate solver. MCMC sampling of the fine-scale parameters is enabled by utilizing the posterior information in the immediate coarser-scale. In this way, the global features are identified in the coarse-scale with inference of low-dimensional variables and inexpensive forward computation, and the local features are refined and corrected in the fine-scale. The developed method is demonstrated with two types of permeability estimation for flow in heterogeneous media. One is a Gaussian random field (GRF) with uncertain length scales, and the other is channelized permeability with the two regions defined by different GRFs. The obtained results indicate that the method allows high-dimensional parameter estimation while exhibiting stability, efficiency and accuracy.
References in corpus (30)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- Variational Inference: A Review for Statisticians
- NICE: Non-linear Independent Components Estimation
- Variational Inference with Normalizing Flows
- Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
- A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
- Training-image based geostatistical inversion using a spatial generative adversarial neural network
- Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
- Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification
- Towards a Definition of Disentangled Representations
- Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
- Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
- Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
- Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
- Adaptive construction of surrogates for the Bayesian solution of inverse problems
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Multilevel Sequential Monte Carlo Samplers
- Solving inverse problems using conditional invertible neural networks
- SCAN: Learning Hierarchical Compositional Visual Concepts
- A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters
- Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
- Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion
- Predictive Collective Variable Discovery with Deep Bayesian Models
- A variational Bayesian method for inverse problems with impulsive noise
- An adaptive reduced basis ANOVA method for high-dimensional Bayesian inverse problems
- ANOVA Gaussian process modeling for high-dimensional stochastic computational models
- Multilevel Dimension-Independent Likelihood-Informed MCMC for Large-Scale Inverse Problems
- Training VAEs Under Structured Residuals