Mitigating greenhouse gas emissions by underground carbon dioxide storage or by coupling intermittent renewable energy with underground hydrogen storage are solutions essential to the future of energy. Of particular importance to the success of underground storage is the fundamental understanding of geochemical reactions with mineralogical phases and flow behavior at the length scale at which interfaces are well resolved. Fast synchrotron-based three-dimensional x-ray microcomputed tomography (\textmu{}CT) of rocks is a widely used technique that provides real-time visualization of fluid flow and transport mechanisms. However, fast imaging results in significant noise and artifacts that complicate the extraction of quantitative data beyond the basic identification of solid and void regions. To address this issue, an image-processing workflow is introduced that begins with unpaired domain transfer by cycle-consistent adversarial network, which is used to transfer synchrotron-based \textmu{}CT images containing fast-imaging-associated noise to long-scan high-quality \textmu{}CT images that have paired ground truth labels for all phases. The second part of the workflow is multimineral segmentation of images using convolutional neural networks (CNNs). Four CNNs are trained using the transferred dynamic-style \textmu{}CT images. A quantitative assessment of physically meaningful parameters and material properties is carried out. In terms of physical accuracy, the results show a high variance for each network output, which indicates that the segmentation performance cannot be fully revealed by pixel-wise accuracy alone. Overall, the integration of unpaired domain transfer with CNN-based multimineral segmentation provides a generalizable digital material framework to study the physics of porous materials for energy-related applications, such as underground ${\mathrm{CO}}_{2}$ and ${\mathrm{H}}_{2}$ storage. 

Generalizable Framework of Unpaired Domain Transfer and Deep Learning for the Processing of Real-Time Synchrotron-Based X-Ray Microcomputed Tomography Images of Complex Structures

Coring induced fractures: indicators of hydraulic fracture propagation in a naturally fractured reservoir.


 Mining subsidence disasters are common geological disasters. Accurate and effective identification of their deformation position is significant in preventing and controlling geological disasters and monitoring illegal mining. In this study, we used deep learning combined with support vector machine (SVM) to establish an automatic detection method for mining subsidence basins using Sentinel-1A data. The Huainan mining area was selected as the experimental area to verify the method. The interferogram was obtained using differential radar interferometry (D-InSAR), and the mining subsidence basin and other targets were extracted manually as training samples. Subsequently, AlexNet, VGG19, and ResNet50 convolutional neural networks (CNNs) were used to extract feature vectors of mining subsidence basins for the SVM classifier, and mining subsidence basins were detected in a large-area InSAR interferogram; The artificial fish swarm algorithm with strong optimization ability and good global convergence is introduced into SVM parameter optimization to construct an improved ResNet50_ SVM model. The experimental results show that (1) the three CNN_SVM methods can accurately detect dry mining subsidence basins automatically in large regional interference maps, providing an essential scientific basis for the government to monitor illegal mining activities and prevent and control geological disasters in mining areas; (2) the accuracy of the CNN_SVM automatic detection methods for mining subsidence basins is approximately 80%, and that of ResNet50_SVM for mining subsidence basin detection is 83.7%, superior to that of AlexNet_SVM and VGG19_SVM, The accuracy of the improved ResNet50_SVM based on AFSA algorithm is 88.3%, which is better than the unimproved Resnet50_SVM model.

Automatic Detection Method of Mining subsidence basin based on InSAR and CNN-AFSA-SVM

Abstract. Studying porous rocks with X-ray computed tomography (XRCT) has been established as a standard procedure for the non-destructive characterization of flow and transport in porous media. Despite the recent advances in the field of XRCT, various challenges still remain due to the inherent noise and imaging artifacts in the produced data. These issues become even more profound when the objective is the identification of fractures and/or fracture networks. One challenge is the limited contrast between the regions of interest and the neighboring areas, which can mostly be attributed to the minute aperture of the fractures. In order to overcome this challenge, it has been a common approach to apply various digital image processing steps, such as filtering, to enhance the signal-to-noise ratio. Additionally, segmentation methods based on threshold/morphology schemes have been employed to obtain enhanced information from the features of interest. However, this workflow needs a skillful operator to fine-tune its input parameters, and the required computation time significantly increases due to the complexity of the available methods and the large volume of an XRCT dataset. In this study, based on a dataset produced by the successful visualization of a fracture network in Carrara marble with micro X-ray computed tomography (μXRCT), we present the results from five segmentation methods, three conventional and two machine-learning-based ones. The objective is to provide the interested reader with a comprehensive comparison between existing approaches while presenting the operating principles, advantages and limitations, to serve as a guide towards an individualized segmentation workflow. The segmentation results from all five methods are compared to each other in terms of quality and time efficiency. Due to memory limitations, and in order to accomplish a fair comparison, all the methods are employed in a 2D scheme. The output of the 2D U-net model, which is one of the adopted machine-learning-based segmentation methods, shows the best performance regarding the quality of segmentation and the required processing time. 

/pdf/detecting-micro-fractures-a-comprehensive-comparison-of-36bami9g.pdf

Detecting micro fractures: a comprehensive comparison of conventional and machine-learning-based segmentation methods

Mining subsidence disasters are common geological disasters. Accurate and effective identification of their deformation position is significant in preventing and controlling geological disasters and monitoring illegal mining. In this study, deep learning, combined with a support vector machine (SVM), has been used to establish an automatic-detection method for mining subsidence basins using Sentinel-1A data. The Huainan mining area was selected as the experimental area to verify the method. The interferogram was obtained using differential radar interferometry (D-InSAR) to process the Sentinel-1A radar data of seven landscapes, and the mining subsidence basin and other targets were extracted manually as training samples. Subsequently, AlexNet, VGG19, and ResNet50 convolutional neural networks (CNNs) were used to extract feature vectors of mining subsidence basins for the SVM classifier, and mining subsidence basins were detected in a large-area InSAR interferogram. Non-maximum suppression was used to remove the repeated search box to improve the detection accuracy of mining subsidence basins; the artificial fish swarm algorithm with strong optimization ability and good global convergence is introduced into SVM parameter optimization to construct an improved ResNet50_SVM model. The experimental results show that: (1) the three CNN_SVM methods can accurately detect dry-mining subsidence basins automatically in large regional interference maps, providing an essential scientific basis for the government to monitor illegal mining activities and prevent and control geological disasters in mining areas; (2) the accuracy of the CNN_SVM automatic-detection methods for mining subsidence basins is approximately 80%, and that of ResNet50_SVM for mining subsidence basin detection is 83.7%, superior to that of AlexNet_SVM and VGG19_SVM; (3) the accuracy of the improved ResNet50_SVM based on AFSA algorithm is 88.3%, which is better than the unimproved Resnet50_SVM model. 

/pdf/automatic-detection-method-for-mining-subsidence-basins-3akj5nyl.pdf

Automatic-Detection Method for Mining Subsidence Basins Based on InSAR and CNN-AFSA-SVM

Automatic fracture detection and characterization from unwrapped drill-core images using mask R–CNN

Dynamic X-ray micotomography of microfibrous cellulose liquid foams using deep learning

The influence of core-scale heterogeneity on continuum-scale flow and laboratory measurements are not well understood. To address this issue, we propose a fully automated workflow based on soft computing to characterize the heterogeneous flow properties of cores for predictive continuum-scale models. While the proposed AI-based workflow inherently has no trained knowledge of rock petrophysical properties, our results demonstrate that image features and morphological properties provide sufficient measures for petrophysical classification. Micro X-ray computed tomography (μxCT) image features were extracted from full core plug images by using a Convolutional Neural Network and Minkowski functional measurements. The features were then classified into specific classes using Principal Component Analysis followed by K-means clustering. Next, the petrophysical properties of each class were evaluated using pore-scale simulations to substantiate that unique classes were identified. The μxCT image was then up-scaled to a continuum-scale grid based on the defined classes. Last, simulation results were evaluated against real-time flooding data monitored by Positron Emission Tomography. Both homogeneous sandstone and heterogeneous carbonate were tested. Simulation and experimental saturation profiles compared well, demonstrating that the workflow provided high-fidelity characterization. Overall, we provided a novel workflow to build digital rock models in a fully automated way to better understand the impacts of heterogeneity on flow. 

Linda Jakob Sadeh

Papers

Automatic fracture detection and characterization from unwrapped drill-core images using mask R–CNN

Automatic fracture detection and characterization from unwrapped drill-core images using mask R–CNN

Dynamic X-ray micotomography of microfibrous cellulose liquid foams using deep learning

Dynamic X-ray micotomography of microfibrous cellulose liquid foams using deep learning

Predictive Soft Computing Methods for Building Digital Rock Models Verified by Positron Emission Tomography Experiments