Leveraging machine learning in porous media

M Delpisheh, B Ebrahimpour, A Fattahi… - Journal of Materials …, 2024‏ - pubs.rsc.org
The emergence of artificial intelligence (AI) and, more particularly, machine learning (ML),
has had a significant impact on engineering and the fundamental sciences, resulting in …

Towards full-stack deep learning-empowered data processing pipeline for synchrotron tomography experiments

Z Zhang, C Li, W Wang, Z Dong, G Liu, Y Dong… - The Innovation, 2024‏ - cell.com
Synchrotron tomography experiments are transitioning into multifunctional, cross-scale, and
dynamic characterizations, enabled by new-generation synchrotron light sources and fast …

Prediction of fluid flow in porous media by sparse observations and physics-informed PointNet

A Kashefi, T Mukerji - Neural Networks, 2023‏ - Elsevier
We predict steady-state Stokes flow of fluids within porous media at pore scales using
sparse point observations and a novel class of physics-informed neural networks, called …

SeisGAN: Improving seismic image resolution and reducing random noise using a generative adversarial network

L Lin, Z Zhong, C Cai, C Li, H Zhang - Mathematical Geosciences, 2024‏ - Springer
Seismic images are essential for understanding the subsurface geological structure and
resource distribution. However, the accuracy and certainty of geological analysis using …

Hierarchical homogenization with deep‐learning‐based surrogate model for rapid estimation of effective permeability from digital rocks

M Liu, R Ahmad, W Cai, T Mukerji - Journal of Geophysical …, 2023‏ - Wiley Online Library
Effective permeability is a key physical property of porous media that defines its ability to
transport fluid. Digital rock physics (DRP) combines modern tomographic imaging …

An end-to-end approach to predict physical properties of heterogeneous porous media: Coupling deep learning and physics-based features

Y Wu, S An, P Tahmasebi, K Liu, C Lin, S Kamrava… - Fuel, 2023‏ - Elsevier
Digital rock physics (DRP) has become an effective tool to predict the petrophysical
properties of rocks and reveal the mass transport mechanisms in porous media. Accurate …

Efficiently reconstructing high-quality details of 3D digital rocks with super-resolution Transformer

Z **ng, J Yao, L Liu, H Sun - Energy, 2024‏ - Elsevier
Accurate pore-scale modeling demands high-quality digital rock images, which should
possess a broad imaging field of view (FOV) and high resolution to characterize multi-scale …

[HTML][HTML] Generating three-dimensional bioinspired microstructures using transformer-based generative adversarial network

YH Chiang, BY Tseng, JP Wang, YW Chen… - Journal of Materials …, 2023‏ - Elsevier
Biomaterials possess extraordinary properties due to intricate structures on the microscale.
Learning from these microstructures is critical for the design of high-performance materials …

A Customized Multi‐Scale Deep Learning Framework for Storm Nowcasting

S Yang, H Yuan - Geophysical Research Letters, 2023‏ - Wiley Online Library
Storm nowcasting is critical and urgently needed. Recent advances in deep learning (DL)
have shown potential for improving nowcasting accuracy and predicting general low …

Multiscale fusion of tight sandstone digital rocks using attention-guided generative adversarial network

P Chi, J Sun, W Yan, X Luo - Marine and Petroleum Geology, 2024‏ - Elsevier
Tight sandstone exhibits heterogeneity due to its multiple mineral compositions and
multiscale pore structures, presenting significant challenges for digital rock modeling. To …