2D-to-3D image translation of complex nanoporous volumes using generative networks

Abstract

Image-based characterization offers a powerful approach to studying geological porous media at the nanoscale and images are critical to understanding reactive transport mechanisms in reservoirs relevant to energy and sustainability technologies such as carbon sequestration, subsurface hydrogen storage, and natural gas recovery. Nanoimaging presents a trade off, however, between higher-contrast sample-destructive and lower-contrast sample-preserving imaging modalities. Furthermore, high-contrast imaging modalities often acquire only 2D images, while 3D volumes are needed to characterize fully a source rock sample. In this work, we present deep learning image translation models to predict high-contrast focused ion beam-scanning electron microscopy (FIB-SEM) image volumes from transmission X-ray microscopy (TXM) images when only 2D paired training data is available. We introduce a regularization method for improving 3D volume generation from 2D-to-2D deep learning image models and apply this approach to translate 3D TXM volumes to FIB-SEM fidelity. We then segment a predicted FIB-SEM volume into a flow simulation domain and calculate the sample apparent permeability using a lattice Boltzmann method (LBM) technique. Results show that our image translation approach produces simulation domains suitable for flow visualization and allows for accurate characterization of petrophysical properties from non-destructive imaging data.

Exploring microstructure and petrophysical properties of microporous volcanic rocks through 3D multiscale and super-resolution imaging

“…Here, we employed pix2pix 50 , a c-GAN with a generator based on a U-Net architecture (revealed the best CNN for our rock). It was developed to be a general-purpose solution to many image-to-image translation tasks 50 and has been recently employed also for multimodal imaging of digital rocks 51 , 52 . The discriminator network, called PatchGAN, is a multi-layer CNN classifier mainly restricted to model high-frequency structures in local image (70 × 70 px) subpatches, on which it classifies an image as real or fake (Fig.…”

Chemical and Reactive Transport Processes Associated with Hydraulic Fracturing of Unconventional Oil/Gas Shales

“…151 Even if acquired at nominally the same spatial resolution, a CT image tends to have lesser contrast in grayscale values and will experience some washing out of fine details. Anderson et al (2020) 151,152 show how to use a few spatially correlated nanoCT and SEM images to train a machine learning algorithm to improve contrast in nanoCT images, thereby reducing the need for destructive SEM imaging to obtain highcontrast images. Figure 18 is an example of a synchrotron X-ray CT image of the Green River shale before and after reaction with acidic HFF.…”