arXiv subjects

Masoud Babaei

Publications and source records attributed to Masoud Babaei.

8 recordsLinked to original sources

arXiv2026

A Decade of Generative Adversarial Networks for Porous Material Reconstruction

Digital reconstruction of porous materials has become increasingly critical for applications ranging from geological reservoir characterization to tissue engineering and electrochemical device design. While traditional methods such as micro-computed tomography and statistical reconstruction approaches have established foundations in this field, the emergence of deep learning techniques, particularly Generative Adversarial Networks (GANs), has revolutionized porous media reconstruction capabilities. This review systematically analyzes 96 peer-reviewed articles published from 2017 to early 2026, examining the evolution and applications of GAN-based approaches for porous material image reconstruction. We categorize GAN architectures into six distinct classes, namely Vanilla GANs, Multi-Scale GANs, Conditional GANs, Attention-Enhanced GANs, Style-based GANs, and Hybrid Architecture GANs. Our analysis reveals substantial progress including improvements in porosity accuracy (within 1% of original samples), permeability prediction (up to 79% reduction in mean relative errors), and achievable reconstruction volumes (from initial $64^3$ to current $2{,}200^3$ voxels). Despite these advances, persistent challenges remain in computational efficiency, memory constraints for large-scale reconstruction, and maintaining structural continuity in 2D-to-3D transformations. This systematic analysis provides a comprehensive framework for selecting appropriate GAN architectures based on specific application requirements.

cs.CV↗

arXiv2025

PCP-GAN: Property-Constrained Pore-scale image reconstruction via conditional Generative Adversarial Networks

Obtaining truly representative pore-scale images that match bulk formation properties remains a fundamental challenge in subsurface characterization, as natural spatial heterogeneity causes extracted sub-images to deviate significantly from core-measured values. This challenge is compounded by data scarcity, where physical samples are only available at sparse well locations. This study presents a multi-conditional Generative Adversarial Network (cGAN) framework that generates representative pore-scale images with precisely controlled properties. The framework was trained on thin section samples from four depths (1879.50-1943.50 m) of a carbonate formation, simultaneously conditioning on porosity and depth within a single model. It processes RGB thin section images that preserve critical mineralogical information (anhydrite-dolomite differentiation, grain boundaries, porosity distinctions) lost in conventional grayscale representations, capturing characteristics from grainstone fabrics to crystalline textures with anhydrite inclusions. The model achieved strong porosity control (R^2 = 0.95) across all formations with mean absolute errors of 0.0099-0.0197. Morphological validation confirmed preservation of average pore radius, specific surface area, and tortuosity within acceptable tolerances. Two-point correlation (S2) analysis confirmed that generated images preserve the spatial continuity and characteristic length scales of natural pore networks, with results consistent across the imaging resolutions tested (1.8-3.0 micron/pixel). Validated against core sample properties, generated images showed higher property fidelity with dual-constraint errors of 1.9-12.4% compared to 37.5-713.6% for randomly extracted real sub-images. This capability provides practical tools for subsurface characterization, particularly valuable for carbon storage, geothermal energy, and groundwater management.

cs.CV↗

arXiv2025

Molecular Insights into Caprock Integrity of Subsurface Hydrogen Storage: Perspective on Hydrogen-induced Swelling and Mechanical Response

The geological storage of hydrogen (H_2) requires reliable long-term caprock sealing, yet the nanoscale interactions between H_2 and clay minerals remain critically underexplored despite their importance for storage security. This lack of understanding has limited the ability to predict mechanical stability and leakage risks in H_2 storage formations. Using molecular simulations, this study investigates the swelling behavior and mechanical properties of sodium montmorillonite (Mt), a common smectite clay, under varying hydration states and interlayer H_2 contents. Results show that H_2 accelerates hydration-state transitions, narrows the stability window of crystalline swelling, and promotes asymmetric plume formation in confined interlayers. H_2 alters cation and water coordination, thereby weakening Na^+--Mt electrostatic interactions and modulating H-bond networks at the interface and in the bulk. Mechanical analysis reveals pronounced anisotropy in Mt. In-plane stiffness is mainly governed by basal spacing expansion, whereas out-of-plane stiffness is highly sensitive to the initial presence of water or H_2, which weaken interlayer cohesion. Tensile and compressive strengths in the in-plane directions follow in-plane stiffness trends, while the out-of-plane tensile strength is governed by Mt--water H-bonds. The presence of H_2 further promotes Mt sheets separation by disrupting nanoscale liquid bridges. Collectively, these results provide the first atomistic-scale evidence that intercalated H_2 reshapes swelling energetics, elastic anisotropy, and failure pathways in Mt, highlighting critical nanoscale mechanisms that may compromise caprock integrity during underground H_2 storage.

cond-mat.mtrl-sci↗

arXiv2024

Geomechanics Contribution to CO2 Storage Containment and Trapping Mechanisms in Tight Sandstone Complexes: A Case Study on Mae Moh Basin

Recognized as a not-an-option approach to mitigate the climate crisis, carbon dioxide capture and storage (CCS) has a potential as much as gigaton of CO2 to sequestrate permanently and securely. Recent attention has been paid to store highly concentrated point-source CO2 into saline formation, of which Thailand considers one onshore case in the north located in Lampang, the Mae Moh coal-fired power plant matched with its own coal mine of Mae Moh Basin. The current study is thus aimed to examine the influence of reservoir geomechanics on CO2 storage containment and trapping mechanisms, with co-contributions from geochemistry and reservoir heterogeneity, using reservoir simulator, CMG-GEM. With the injection rate designed for 30-year injection, reservoir pressure build-ups were 77% of fracture pressure but increased to 80% when geomechanics excluded. Such pressure responses imply that storage security is associated with the geomechanics. Dominated by viscous force, CO2 plume migrated more laterally while geomechanics clearly contributed to lesser migration due to reservoir rock strength constraint. Reservoir geomechanics contributed to less plume traveling into more constrained spaces while leakage was secured, highlighting a significant and neglected influence of geomechanical factor. Spatiotemporal development of CO2 plume also confirms the geomechanics-dominant storage containment. Reservoir geomechanics as attributed to its respective reservoir fluid pressure controls development of trapping mechanisms, especially into residual and solubility traps. More secured storage containment after the injection was found with higher pressure, while less development into solubility trap was observed with lower pressure.

physics.geo-ph↗

arXiv2022

DeepAngle: Fast calculation of contact angles in tomography images using deep learning

DeepAngle is a machine learning-based method to determine the contact angles of different phases in the tomography images of porous materials. Measurement of angles in 3--D needs to be done within the surface perpendicular to the angle planes, and it could become inaccurate when dealing with the discretized space of the image voxels. A computationally intensive solution is to correlate and vectorize all surfaces using an adaptable grid, and then measure the angles within the desired planes. On the contrary, the present study provides a rapid and low-cost technique powered by deep learning to estimate the interfacial angles directly from images. DeepAngle is tested on both synthetic and realistic images against the direct measurement technique and found to improve the r-squared by 5 to 16% while lowering the computational cost 20 times. This rapid method is especially applicable for processing large tomography data and time-resolved images, which is computationally intensive. The developed code and the dataset are available at an open repository on GitHub (https://www.github.com/ArashRabbani/DeepAngle).

cs.CV↗

arXiv2022

Automated segmentation and morphological characterization of placental histology images based on a single labeled image

In this study, a novel method of data augmentation has been presented for the segmentation of placental histological images when the labeled data are scarce. This method generates new realizations of the placenta intervillous morphology while maintaining the general textures and orientations. As a result, a diversified artificial dataset of images is generated that can be used for training deep learning segmentation models. We have observed that on average the presented method of data augmentation led to a 42% decrease in the binary cross-entropy loss of the validation dataset compared to the common approach in the literature. Additionally, the morphology of the intervillous space is studied under the effect of the proposed image reconstruction technique, and the diversity of the artificially generated population is quantified. Due to the high resemblance of the generated images to the real ones, the applications of the proposed method may not be limited to placental histological images, and it is recommended that other types of tissues be investigated in future studies.

eess.IV↗

arXiv2022

Resolution enhancement of placenta histological images using deep learning

In this study, a method has been developed to improve the resolution of histological human placenta images. For this purpose, a paired series of high- and low-resolution images have been collected to train a deep neural network model that can predict image residuals required to improve the resolution of the input images. A modified version of the U-net neural network model has been tailored to find the relationship between the low resolution and residual images. After training for 900 epochs on an augmented dataset of 1000 images, the relative mean squared error of 0.003 is achieved for the prediction of 320 test images. The proposed method has not only improved the contrast of the low-resolution images at the edges of cells but added critical details and textures that mimic high-resolution images of placenta villous space.

eess.IV↗

arXiv2020

DeePore: a deep learning workflow for rapid and comprehensive characterization of porous materials

DeePore is a deep learning workflow for rapid estimation of a wide range of porous material properties based on the binarized micro-tomography images. By combining naturally occurring porous textures we generated 17700 semi-real 3-D micro-structures of porous geo-materials with size of 256^3 voxels and 30 physical properties of each sample are calculated using physical simulations on the corresponding pore network models. Next, a designed feed-forward convolutional neural network (CNN) is trained based on the dataset to estimate several morphological, hydraulic, electrical, and mechanical characteristics of the porous material in a fraction of a second. In order to fine-tune the CNN design, we tested 9 different training scenarios and selected the one with the highest average coefficient of determination (R^2) equal to 0.885 for 1418 testing samples. Additionally, 3 independent synthetic images as well as 3 realistic tomography images have been tested using the proposed method and results are compared with pore network modelling and experimental data, respectively. Tested absolute permeabilities had around 13 % relative error compared to the experimental data which is noticeable considering the accuracy of the direct numerical simulation methods such as Lattice Boltzmann and Finite Volume. The workflow is compatible with any physical size of the images due to its dimensionless approach and can be used to characterize large-scale 3-D images by averaging the model outputs for a sliding window that scans the whole geometry.

cond-mat.mtrl-sci↗