Stochastic reconstruction of an oolitic limestone by generative adversarial networks

TL;DR

This paper introduces a 3D stochastic image reconstruction method for oolitic limestone microstructures using generative adversarial networks, enabling fast, accurate, and unsupervised sampling for digital rock physics.

Contribution

The paper demonstrates the application of GANs for 3D microstructure reconstruction, addressing challenges in evaluating generative models in this context.

Findings

GANs enable fast sampling of large volumetric images

Reconstructed images match key morphological and flow properties

The method improves efficiency in digital rock physics simulations

Abstract

Stochastic image reconstruction is a key part of modern digital rock physics and materials analysis that aims to create numerous representative samples of material micro-structures for upscaling, numerical computation of effective properties and uncertainty quantification. We present a method of three-dimensional stochastic image reconstruction based on generative adversarial neural networks (GANs). GANs represent a framework of unsupervised learning methods that require no a priori inference of the probability distribution associated with the training data. Using a fully convolutional neural network allows fast sampling of large volumetric images.We apply a GAN based workflow of network training and image generation to an oolitic Ketton limestone micro-CT dataset. Minkowski functionals, effective permeability as well as velocity distributions of simulated flow within the acquired images are compared with the synthetic reconstructions generated by the deep neural network. While our results show that GANs allow a fast and accurate reconstruction of the evaluated image dataset, we address a number of open questions and challenges involved in the evaluation of generative network-based methods.