Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network

Abstract

Efficient and high-fidelity prior sampling and inversion for complex geological media is still a largely unsolved challenge. Here, we use a deep neural network of the variational autoencoder type to construct a parametric low-dimensional base model parameterization of complex binary geological media. For inversion purposes, it has the attractive feature that random draws from an uncorrelated standard normal distribution yield model realizations with spatial characteristics that are in agreement with the training set. In comparison with the most commonly used parametric representations in probabilistic inversion, we find that our dimensionality reduction (DR) approach outperforms principle component analysis (PCA), optimization-PCA (OPCA) and discrete cosine transform (DCT) DR techniques for unconditional geostatistical simulation of a channelized prior model. For the considered examples, important compression ratios (200 - 500) are achieved. Given that the construction of our parameterization requires a training set of several tens of thousands of prior model realizations, our DR approach is more suited for probabilistic (or deterministic) inversion than for unconditional (or point-conditioned) geostatistical simulation. Probabilistic inversions of 2D steady-state and 3D transient hydraulic tomography data are used to demonstrate the DR-based inversion. For the 2D case study, the performance is superior compared to current state-of-the-art multiple-point statistics inversion by sequential geostatistical resampling (SGR). Inversion results for the 3D application are also encouraging.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• MCMC using Hamiltonian dynamics
• DRAW: A Recurrent Neural Network For Image Generation
• Distributed soil moisture from crosshole ground-penetrating radar travel times using stochastic inversion
• Summary statistics from training images as prior information in probabilistic inversion
• Image synthesis with graph cuts: a fast model proposal mechanism in probabilistic inversion

Cited by in corpus (31)

• A trans-disciplinary review of deep learning research for water resources scientists
• 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 Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
• Multiphase flow prediction with deep neural networks
• Accurate and Fast reconstruction of Porous Media from Extremely Limited Information Using Conditional Generative Adversarial Network
• Deep-Learning based Inverse Modeling Approaches: A Subsurface Flow Example
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• 3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels
• Efficient Uncertainty Quantification for Dynamic Subsurface Flow with Surrogate by Theory-guided Neural Network
• Solving inverse problems using conditional invertible neural networks
• 3D Bayesian Variational Full Waveform Inversion
• Using Deep Learning to Improve Ensemble Smoother: Applications to Subsurface Characterization
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching
• Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
• An introduction to variational inference in Geophysical inverse problems
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• Informed Proposal Monte Carlo
• DeepFlow: History Matching in the Space of Deep Generative Models
• Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
• Adaptive sequential Monte Carlo for posterior inference and model selection among complex geological priors
• Using deep generative neural networks to account for model errors in Markov chain Monte Carlo inversion
• A Deep Learning-Accelerated Data Assimilation and Forecasting Workflow for Commercial-Scale Geologic Carbon Storage
• A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem with a Convolutional Neural Network
• Data-Space Inversion Using a Recurrent Autoencoder for Time-Series Parameterization
• Diffusion models for multivariate subsurface generation and efficient probabilistic inversion
• Towards Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fields
• Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation