Enhancing images of shale formations by a hybrid stochastic and deep learning algorithm

S Kamrava, P Tahmasebi, M Sahimi - Neural Networks, 2019 - Elsevier
Accounting for the morphology of shale formations, which represent highly heterogeneous
porous media, is a difficult problem. Although two-or three-dimensional images of such …

Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty

W Zha, X Li, Y Xing, L He, D Li - Advances in Geo-Energy Research, 2020 - sciopen.com
Abstract Generative Adversarial Networks (GANs), as most popular artificial intelligence
models in the current image generation field, have excellent image generation capabilities …

Deep learning in pore scale imaging and modeling

Y Da Wang, MJ Blunt, RT Armstrong… - Earth-Science Reviews, 2021 - Elsevier
Pore-scale imaging and modeling has advanced greatly through the integration of Deep
Learning into the workflow, from image processing to simulating physical processes. In …

Stochastic reconstruction of an oolitic limestone by generative adversarial networks

L Mosser, O Dubrule, MJ Blunt - Transport in Porous Media, 2018 - Springer
Stochastic image reconstruction is a key part of modern digital rock physics and material
analysis that aims to create representative samples of microstructures for upsampling …

Multiscale and multiresolution modeling of shales and their flow and morphological properties

P Tahmasebi, F Javadpour, M Sahimi - Scientific reports, 2015 - nature.com
The need for more accessible energy resources makes shale formations increasingly
important. Characterization of such low-permeability formations is complicated, due to the …

Multimodal imaging and machine learning to enhance microscope images of shale

TI Anderson, B Vega, AR Kovscek - Computers & Geosciences, 2020 - Elsevier
A machine learning based image processing workflow is presented to enhance shale
source rock microscopic images obtained using diverse imaging platforms. Images were …

Nanoscale and multiresolution models for shale samples

P Tahmasebi - Fuel, 2018 - Elsevier
Abstract Characterization of shale systems requires imaging at different scales. One reason
can be due to a diverse pore-size distribution. Low-resolution images often cover the large …

Advances in the application of deep learning methods to digital rock technology.

X Li, B Li, F Liu, T Li, X Nie - Advances in Geo-Energy …, 2023 - search.ebscohost.com
Digital rock technology is becoming essential in reservoir engineering and petrophysics.
Three-dimensional digital rock reconstruction, image resolution enhancement, image …

Multiscale study for stochastic characterization of shale samples

P Tahmasebi, F Javadpour, M Sahimi, M Piri - Advances in Water …, 2016 - Elsevier
Abstract Characterization of shale reservoirs, which are typically of low permeability, is very
difficult because of the presence of multiscale structures. While three-dimensional (3D) …

Multiscale modeling of shale samples based on low-and high-resolution images

Y Wu, P Tahmasebi, C Lin, L Ren, C Dong - Marine and Petroleum Geology, 2019 - Elsevier
Accurate modeling of shale samples is very crucial for evaluating and predicting the physical
properties. However, obtaining large-scale and high-resolution images of shales using a …