Reconstruction of three-dimensional porous media using generative adversarial neural networks

Abstract

To evaluate the variability of multi-phase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a novel method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image datasets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that GANs can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.

21 pages, 20 figures

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Wasserstein GAN
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Amortised MAP Inference for Image Super-resolution

Cited by in corpus (59)

• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Training-image based geostatistical inversion using a spatial generative adversarial neural network
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Generating 3D structures from a 2D slice with GAN-based dimensionality expansion
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• Seeing Permeability From Images: Fast Prediction with Convolutional Neural Networks
• 70 years of machine learning in geoscience in review
• Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Deep Learning in Deterministic Computational Mechanics
• Industrial applications of digital rock technology
• Parametric generation of conditional geological realizations using generative neural networks
• Accurate and Fast reconstruction of Porous Media from Extremely Limited Information Using Conditional Generative Adversarial Network
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• DeePore: a deep learning workflow for rapid and comprehensive characterization of porous materials
• Regressive and generative neural networks for scalar field theory
• Microstructure synthesis using style-based generative adversarial network
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Solving inverse problems using conditional invertible neural networks
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• Parametrization and generation of geological models with generative adversarial networks
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics
• Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks
• Digital rock reconstruction with user-defined properties using conditional generative adversarial networks
• When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy
• Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions
• Precise algorithms to compute surface correlation functions of two-phase heterogeneous media and their applications
• Modeling nanoconfinement effects using active learning
• RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation
• DeepFlow: History Matching in the Space of Deep Generative Models
• Adaptive phase-retrieval stochastic reconstruction with correlation functions: 3D images from 2D cuts
• Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks
• Morphology Decoder: A Machine Learning Guided 3D Vision Quantifying Heterogenous Rock Permeability for Planetary Surveillance and Robotic Functions
• Enforcing Deterministic Constraints on Generative Adversarial Networks for Emulating Physical Systems
• Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
• Multiscale reconstruction of porous media based on multiple dictionaries learning
• Adaptive sequential Monte Carlo for posterior inference and model selection among complex geological priors
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• A Deep-Learning-Based Geological Parameterization for History Matching Complex Models
• Mitigation of Spatial Nonstationarity with Vision Transformers
• Controlled Latent Diffusion Models for 3D Porous Media Reconstruction
• Deep Learning Convective Flow Using Conditional Generative Adversarial Networks
• Reconstruction of 3D Porous Media From 2D Slices
• Data-Space Inversion Using a Recurrent Autoencoder for Time-Series Parameterization
• Pores for thought: The use of generative adversarial networks for the stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries
• Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks
• How good is my GAN?
• A statistical framework for generating microstructures of two-phase random materials: application to fatigue analysis
• PorousGen: An Efficient Algorithm for Generating Porous Structures with Accurate Porosity and Uniform Density Distribution
• Simulating volume-controlled invasion of a non-wetting fluid in volumetric images using basic image processing tools
• Deep learning regression for inverse quantum scattering
• Generation of non-stationary stochastic fields using Generative Adversarial Networks
• AI-driven Bayesian inference of statistical microstructure descriptors from finite-frequency waves
• Sojourn functionals for spatiotemporal random fields with long-memory
• A Unified Pore-Scale Multiphysics Model for the Integrated Soot Transport-Deposition-Oxidation in Catalytic Diesel Particulate Filters