Deep neural networks for improving physical accuracy of 2D and 3D multi-mineral segmentation of rock micro-CT images

Sandification degree classification of sandy dolomite base on convolutional neural networks

Sandification can degrade the strength and quality of dolomite, and to a certain extent, compromise the stability of a tunnel's surrounding rock as an unfavorable geological boundary. Sandification degree classification of sandy dolomite is one of the non-trivial challenges faced by geotechnical engineering projects such as tunneling in complex geographical environments. The traditional methods quantitatively measuring the physical parameters or analyzing some visual features are either time-consuming or inaccurate in practical use. To address these issues, we, for the first time, introduce the convolutional neural network (CNN)-based image classification methods into dolomite sandification degree classification task. In this study, we have made a significant contribution by establishing a large-scale dataset comprising 5729 images, classified into four distinct sandification degrees of sandy dolomite. These images were collected from the vicinity of a tunnel located in the Yuxi section of the CYWD Project in China. We conducted comprehensive classification experiments using this dataset. The results of these experiments demonstrate the groundbreaking achievement of CNN-based models, which achieved an impressive accuracy rate of up to 91.4%. This accomplishment underscores the pioneering role of our work in creating this dataset and its potential for applications in complex geographical analyses.

Comparative study on convolutional neural network and regression analysis to evaluate uniaxial compressive strength of Sandy Dolomite

Sandy Dolomite is a kind of widely distributed rock. The uniaxial compressive strength (UCS) of Sandy Dolomite is an important metric in the application in civil engineering, geotechnical engineering, and underground engineering. Direct measurement of UCS is costly, time-consuming, and even infeasible in some cases. To address this problem, we establish an indirect measuring method based on the convolutional neural network (CNN) and regression analysis (RA). The new method is straightforward and effective for UCS prediction, and has significant practical implications. To evaluate the performance of the new method, 158 dolomite samples of different sandification grades are collected for testing their UCS along and near the Yuxi section of the Central Yunnan Water Diversion (CYWD) Project in Yunnan Province, Southwest of China. Two regression equations with high correlation coefficients are established according to the RA results, to predict the UCS of Sandy Dolomites. Moreover, the minimum thickness of Sandy Dolomite was determined by the Schmidt hammer rebound test. Results show that CNN outperforms RA in terms of prediction the precision of Sandy Dolomite UCS. In addition, CNN can effectively deal with uncertainty in test results, making it one of the most effective tools for predicting the UCS of Sandy Dolomite.

Comprehensive Analysis of Connectivity and Permeability of a Pore-Fracture Structure in Low Permeability Seam of Huainan-Huaibei Coalfield

The connectivity and permeability of the coal seam pore structures control the occurrence and migration of coalbed methane. Coal samples were used from Huainan-Huaibei to reconstruct three-dimensional models of the pores and an equivalent pore network model, Statistical pore structure characteristic parameters. The pore structure of the coal reservoir was analyzed from the direction of multidimensional and multiangle. It shows that based on quantitative analysis, the representative Elementary volume of 500 × 500 × 500 was the most suitable experimental volume. The Y-axis direction of the Renlou sample had poor pore connectivity compared to that of other samples. Large volume connected pores dominated their pore systems. In terms of coal sample pore connectivity, the coal samples from the Liuzhuang and Qidong regions had pore connectivity better than those from the other regions. The pore connectivity of the Liuzhuang coal samples was the best. In terms of coal permeability, the Liuzhuang sample had better permeability than the other three samples, and the permeability was the best in the Y-axis direction. For all the combinations of the different types of throats, the shorter the throat, the greater the equivalent radius and the better the permeability. Conversely, the worse the permeability. During gas injection production, the closer the gas injection area was to the gas injection well, the poorer the connectivity and the lower the permeability over time. Near the production area, where the CO2 did not reach the production area, the fracture porosity and effective connected porosity of the coal reservoir increased over time. When CO2 reached the production area, the change in its connected pore structure was consistent with the change in the connected pores in the gas injection area. With this study, the coal seam pore structure on a microscale was characterized. A comprehensive analysis of the coal reservoir pore connectivity and permeability was completed. The study results are significant for the exploration and development of coalbed methane in the Huainan-Huaibei coalfield.

In situ characterization of heterogeneous surface wetting in porous materials

The performance of nano- and micro-porous materials in capturing and releasing fluids, such as during CO2 geo-storage and water/gas removal in fuel cells and electrolyzers, is determined by their wettability in contact with the solid. However, accurately characterizing wettability is challenging due to spatial variations in dynamic forces, chemical heterogeneity, and surface roughness. In situ measurements can potentially measure wettability locally as a contact angle - the angle a denser phase (e.g water) contacts solid in the presence of a second phase (e.g. hydrogen, air, CO2) - but suffer from difficulties in accurately capturing curvatures, contact areas, and contact loops of multiphase fluids. We introduce a novel extended topological method for in situ contact angle measurement and provide a comparative review of current geometric and topological methods, assessing their accuracy on ideal surfaces, porous rocks containing CO2, and water in gas diffusion layers. The new method demonstrates higher accuracy and reliability of in situ measurements for uniformly wetting systems compared to previous topological approaches, while geometric measurements perform best for mixed-wetting domains. This study further provides a comprehensive open-source platform for in situ characterization of wettability in porous materials with implications for gas geo-storage, fuel cells and electrolyzers, filtration, and catalysis.

Coupled Lattice Boltzmann Modeling Framework for Pore-Scale Fluid Flow and Reactive Transport

In this paper, we propose a modeling framework for pore-scale fluid flow and reactive transport based on a coupled lattice Boltzmann model (LBM). We develop a modeling interface to integrate the LBM modeling code parallel lattice Boltzmann solver and the PHREEQC reaction solver using multiple flow and reaction cell mapping schemes. The major advantage of the proposed workflow is the high modeling flexibility obtained by coupling the geochemical model with the LBM fluid flow model. Consequently, the model is capable of executing one or more complex reactions within desired cells while preserving the high data communication efficiency between the two codes. Meanwhile, the developed mapping mechanism enables the flow, diffusion, and reactions in complex pore-scale geometries. We validate the coupled code in a series of benchmark numerical experiments, including 2D single-phase Poiseuille flow and diffusion, 2D reactive transport with calcite dissolution, as well as surface complexation reactions. The simulation results show good agreement with analytical solutions, experimental data, and multiple other simulation codes. In addition, we design an AI-based optimization workflow and implement it on the surface complexation model to enable increased capacity of the coupled modeling framework. Compared to the manual tuning results proposed in the literature, our workflow demonstrates fast and reliable model optimization results without incorporating pre-existing domain knowledge.

Correlation Evaluation and Schematic Analysis of Influencing Factors Affecting Pore and Fracture Connectivity on the Microscale and Their Application Discussion in Coal Reservoir Based on X-ray CT Data

The connectivity of the pore/fracture system is the key to CO₂ injection and CH₄ production, which is of great significance in analyzing the correlation and weight of the influencing factors affecting the connectivity on the microscale. First, the 3D reconstruction of the coal reservoir is realized. Second, the characteristic parameters of pore/fracture structures are analyzed. Next, the characteristics of absolute permeability are analyzed, and then the correlation and weight analysis of the influencing factors are realized. Finally, the schematic analysis and application discussion of the influencing factors are carried out. The results show that porosity is the key factor restricting fluid migration. The heterogeneity of the reservoir can be characterized by the volume changes of the pore/fracture, organic matter, and mineral. The interconnected pores/fractures are mainly distributed in sheets and bands. The coordination number ranges from 1 to 15. The Ferret diameter is 0-10 μm. The tortuosity is 2.27111, 1.9034, 3.98522, and 3.51516, respectively, and the Euler characteristic number is 0.931868, 0.974719, 0.921144, and 0.897697, respectively. The permeability of the SH and YW samples is higher than that of the RL and PY samples. The single weight of the influencing factor is as follows: coordination number > Ferret diameter > Euler characteristic number > porosity > tortuosity. The analysis area of the comprehensive evaluation score of the influencing factors and the permeability value can be divided into three grades. There is a positive correlation among the coordination number, the quantity equilibrium of pores and throats, and the connectivity. The shape factor gradually increases with the increase of the Ferret diameter. The reservoir permeability is indirectly characterized by the coordination number, Ferret diameter, tortuosity, Euler characteristic number, and shape factor. This study can provide new ideas for clarifying the correlation degree and weight value of the characteristic parameters and can enrich the development of 3D digital core and CO₂-ECBM technology.

Large-scale physically accurate modelling of real proton exchange membrane fuel cell with deep learning

Proton exchange membrane fuel cells, consuming hydrogen and oxygen to generate clean electricity and water, suffer acute liquid water challenges. Accurate liquid water modelling is inherently challenging due to the multi-phase, multi-component, reactive dynamics within multi-scale, multi-layered porous media. In addition, currently inadequate imaging and modelling capabilities are limiting simulations to small areas (<1 mm²) or simplified architectures. Herein, an advancement in water modelling is achieved using X-ray micro-computed tomography, deep learned super-resolution, multi-label segmentation, and direct multi-phase simulation. The resulting image is the most resolved domain (16 mm² with 700 nm voxel resolution) and the largest direct multi-phase flow simulation of a fuel cell. This generalisable approach unveils multi-scale water clustering and transport mechanisms over large dry and flooded areas in the gas diffusion layer and flow fields, paving the way for next generation proton exchange membrane fuel cells with optimised structures and wettabilities.

Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network

Because of its benefits in terms of high speed, non-destructiveness, and three-dimensionality, as well as ease of integration with computer simulation, computed tomography (CT) technology is widely applied in reservoir geology research. However, rock imaging is restricted by the device used as there is not a win–win for both the image receptive field and corresponding resolution. Convolutional neural network-based super-resolution reconstruction has become a hot topic in improving the performance of CT images. With the help of a convolution kernel, it can effectively extract characteristics and ignore disturbance information. The dismal truth is that convolutional neural networks still have numerous issues, particularly unclear texture details. To address these challenges, a generative adversarial network (RDCA-SRGAN) was designed to improve rock CT image resolution using the combination of residual learning and a dual-channel attention mechanism. Specifically, our generator employs residual attention to extract additional features; similarly, the discriminator builds on dual-channel attention and residual learning to distinguish generated contextual information and decrease computational consumption. Quantitative and qualitative analyses demonstrate that the proposed model is superior to earlier advanced frameworks and is capable to constructure visually indistinguishable high-frequency details. The quantitative analysis shows our model contributes the highest value of structural similarity, enriching the more detailed texture information. From the qualitative analysis, in enlarged details of the reconstructed images, the edges of the images generated by the RDCA-SRGAN can be shown to be clearer and sharper. Our model not only performs well in subtle coal cracks but also enriches more dissolved carbonate and carbon minerals. The RDCA-SRGAN has substantially enhanced the reconstructed image resolution and our model has great potential to be used in geomorphological study and exploration.

Super-Resolved Segmentation of X-ray Images of Carbonate Rocks Using Deep Learning

Reliable quantitative analysis of digital rock images requires precise segmentation and identification of the macroporosity, sub-resolution porosity, and solid\mineral phases. This is highly emphasized in heterogeneous rocks with complex pore size distributions such as carbonates. Multi-label segmentation of carbonates using classic segmentation methods such as multi-thresholding is highly sensitive to user bias and often fails in identifying low-contrast sub-resolution porosity. In recent years, deep learning has introduced efficient and automated algorithms that are capable of handling hard tasks with precision comparable to human performance, with application to digital rocks super-resolution and segmentation emerging. Here, we present a framework for using convolutional neural networks (CNNs) to produce super-resolved segmentations of carbonates rock images for the objective of identifying sub-resolution porosity. The volumes used for training and testing are based on two different carbonates rocks imaged in-house at low and high resolutions. We experiment with various implementations of CNNs architectures where super-resolved segmentation is obtained in an end-to-end scheme and using two networks (super-resolution and segmentation) separately. We show the capability of the trained model of producing accurate segmentation by comparing multiple voxel-wise segmentation accuracy metrics, topological features, and measuring effective properties. The results underline the value of integrating deep learning frameworks in digital rock analysis.

Automatic segmentation tool for 3D digital rocks by deep learning

Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results.