Petrophysical properties are fundamental to understanding fluid flow processes in hydrocarbon reservoirs. Special Core Analysis (SCAL) routinely used in industry are time-consuming, expensive, and often destructive. Alternatively, easily available thin section data is lacking the representation of pore space in 3D, which is a requisite for generating pore network models (PNM) and computing petrophysical properties. In this study, these challenges were addressed using a numerical SCAL workflow that employs pore volume reconstruction from thin section images obtained from confocal laser scanning microscopy (CLSM). A key objective is to investigate methods capable of 2D to 3D reconstruction, to obtain PNM used for the estimation of transport properties. Representative thin sections from a well-known Middle-Eastern carbonate formation were used to obtain CLSM images. The thin-sections were specially prepared by spiking the resin with UV dye, enabling high-resolution imaging. The grayscale images obtained from CLSM were preprocessed and segmented into binary images. Generative Adversarial Networks (GAN) and Two-Point Statistics (TPS) were applied, and PNM were extracted from these binary datasets. Porosity, Permeability, and Mercury Injection Porosimetry (MIP) on the corresponding core plugs were conducted and an assessment of the properties computed from the PNM obtained from the reconstructed 3D pore volume is presented. Moreover, the results from the artificial pore networks were corroborated using 3D confocal images of etched pore casts (PCE). The results showed that based on visual inspection only, GAN outperformed TPS in mimicking the 3D distribution of pore scale heterogeneity, additionally, GAN and PCE outperformed the results of MIP obtained by TPS on the Skeletal-Oolitic facies, without providing a major improvement on more heterogeneous samples. All methods captured successfully the porosity while absolute permeability was not captured. Formation resistivity factor and thermal conductivity showcased their strong correlation with porosity. The study thus provides valuable insights into the application of 2D to 3D reconstruction to obtain pore network models of heterogeneous carbonate rocks for petrophysical characterization for quick decision. The study addresses the following important questions: 1) how legacy thin sections can be leveraged to petrophysically characterize reservoir rocks 2) how reliable are 2D to 3D reconstruction methods when predicting petrophysical properties of carbonates.

Under current technical levels and industrial systems, geological carbon sequestration (GCS) is a viable solution to maintain and further reduce carbon dioxide (CO2) concentration and ensure energy security simultaneously. The pre-injection formation characterization and post-injection CO2 monitoring, verification, and accounting (MVA) are two critical and challenging tasks to guarantee the sequestration effect. The tasks can be accomplished using core analyses and well-logging technologies, which complement each other to produce the most accurate and sufficient subsurface information for pore-scale and reservoir-scale studies. In recent years, the unprecedented data sources, increasing computational capability, and the developments of machine learning (ML) and deep learning (DL) algorithms provide novel perspectives for expanding the knowledge from data, which can capture highly complex nonlinear relationships between multivariate inputs and outputs. This work applied ML and DL methods to GCS-related studies at pore and reservoir scales, including digital rock physics (DRP) and the well-logging data interpretation and analysis. DRP provides cost-saving and practical core analysis methods, combining high-resolution imaging techniques, such as the three-dimensional (3D) X-ray computed tomography (CT) scanning, with advanced numerical simulations. Image segmentation is a crucial step of the DRP framework, affecting the accuracy of the following analyses and simulations. We proposed a DL-based workflow for boundary and small target segmentation in digital rock images, which aims to overcome the main challenge in X-ray CT image segmentation, partial volume blurring (PVB). The training data and the model architecture are critical factors affecting the performance of supervised learning models. We employed the entropy-based-masking indicator kriging (IK-EBM) to generate high-quality training data. The performance of IK-EBM on segmentation affected by PVB was compared with some commonly used image segmentation methods on the synthetic data with known ground truth. We then trained and tested the UNet++ model with nested architecture and redesigned skip connections. The evaluation metrics include the pixel-wise (i.e. F1 score, boundary-scaled accuracy, and pixel-by-pixel comparison) and physics-based (porosity, permeability, and CO2 blob curvature distributions) accuracies. We also visualized the feature maps and tested the model generalizations. Contact angle (CA) distribution quantifies the rock surface wettability, which regulates the multiphase behaviors in the porous media. We developed a DL-based CA measurement workflow by integrating an unsupervised learning pipeline for image segmentation and an open-source CA measurement tool. The image segmentation pipeline includes the model training of a CNN-based unsupervised DL model, which is constrained by feature similarity and spatial continuity. In addition, the over-segmentation strategy was adopted for model training, and the post-processing was implemented to cluster the model output to the user-desired target. The performance of the proposed pipeline was evaluated using synthetic data with known ground truth regarding the pixel-wise and physics-based evaluation metrics. The resulting CA measurements with the segmentation results as input data were validated using manual CA measurements. The GCS projects in the Illinois Basin are the first large-scale injection into saline aquifers and employed the latest pulsed neutron tool, the pulsed neutron eXtreme (PNX), to monitor the injected CO2 saturation. The well-logging data provide valuable references for the formation evaluation and CO2 monitoring in GCS in saline aquifers at the reservoir scale. In addition, data-driven models based on supervised ML and DL algorithms provide a novel perspective for well-logging data analysis and interpretation. We applied two commonly used ML and DL algorithms, support vector machine regression (SVR) and artificial neural network (ANN), to the well-logging dataset from GCS projects in the Illinois Basin. The dataset includes the conventional well-logging data for mineralogy and porosity interpretation and PNX data for CO2 saturation estimation. The model performance was evaluated using the root mean square error (RMSE) and R2 score between model-predicted and true values. The results showed that all the ML and DL models achieved excellent accuracies and high efficiency. In addition, we ranked the feature importance of PNX data in the CO2 saturation estimation models using the permutation importance algorithm, and the formation sigma, pressure, and temperature are the three most significant factors in CO2 saturation estimation models. The major challenge for the CO2 storage field projects is the large-scale real-time data processing, including the pore-scale core and reservoir-scale well-logging data. Compared with the traditional data processing methods, ML and DL methods achieved accuracy and efficiency simultaneously. This work developed ML and DL-based workflows and models for X-ray CT image segmentation and well-logging data interpretations based on the available datasets. The performance of data-driven surrogate models has been validated regarding comprehensive evaluation metrics. The findings fill the knowledge gap regarding formation evaluation and fluid behavior simulation across multiple scales, ensuring sequestration security and effect. In addition, the developed ML and DL workflows and models provide efficient and reliable tools for massive GCS-related data processing, which can be widely used in future GCS projects. / Doctor of Philosophy / Geological carbon sequestration (GCS) is the solution to ease the tension between the increasing carbon dioxide (CO2) concentrations in the atmosphere and the high dependence of human society on fossil energy. The sequestration requires the injection formation to have adequate storage capability, injectivity, and impermeable caprock overlain. Also, the injected CO2 plumes should be monitored in real-time to prevent any migration of CO2 to the surface. Therefore, pre-injection formation characterization and post-injection CO2 saturation monitoring are two critical and challenging tasks to guarantee the sequestration effect and security, which can be accomplished using the combination of pore-scale core analyses and reservoir-scale well-logging technologies. This work applied machine learning (ML) and deep learning (DL) methods to GCS-related studies across multiple spatial scales. We developed supervised and unsupervised DL-based workflows to segment the X-ray computed-tomography (CT) image of digital rocks for the pore-scale studies. Image segmentation is a crucial step in the digital rock physics (DRP) framework, and the following analyses and simulations are conducted on the segmented images. We also developed ML and DL models for well-logging data interpretation to analyze the mineralogy and estimate CO2 saturation. Compared with the traditional well-logging analysis methods, which are usually time-consuming and prior knowledge-dependent, the ML and DL methods achieved comparable accuracy and much shorter processing time. The performance of developed workflows and models was validated regarding comprehensive evaluation metrics, achieving excellent accuracies and high efficiency simultaneously. We are at the early stage of CO2 sequestration, and relevant knowledge and tools are inadequate. In addition, the main challenge of CO2 sequestration field projects is the large-scale and real-time data processing for fast decision-making. The findings of this dissertation fill the knowledge gap in GCS-related formation evaluation and fluid behavior simulations across multiple spatial scales. The developed ML and DL workflows provide efficient and reliable tools for massive data processing, which can be widely used in future GCS projects.

La thèse a pour but d’étudier les effets de changements de mouillabilité de roches dans des conditions d’injections d’eau douce en tant que méthode de récupération d’hydrocarbures. Afin d’identifier le ou les mécanismes à l’origine du gain additionnel de récupération nous avons utilisé un microtomographe RX. Nous avons ainsi imagé les états de saturations finales d’un milieu poreux rempli de saumures et d’huiles. Une fois le drainage primaire réalisé nous avons effectué deux phases d’imbibitions : avec une saumure (récupération secondaire) puis une imbibition d’eau douce (récupération tertiaire). L’analyse de la mouillabilité à l’échelle du pore a permis de mettre en évidence l’effet de la température et de la salinité sur la mouillabilité. Nous avons montré que les changements de mouillages des roches n’étaient pas occasionnées par la seule expansion de la couche électrique en revanche des changements de mouillabilité ont été montrés. Ces changements s’expliquant par des transitions de mouillages de second ordre observées non seulement pour des gouttes d’huiles sur de l’eau mais également sur un substrat en verre. Au final, la mouillabilité en milieux poreux doit être mise en évidence à une échelle sous-Micrométrique ce qui est relativement nouveau dans le domaine pétrolier. / The aim of the thesis is to study rock wettability change effects caused by Low Salinity brine injection as tertiary recovery method. To identify the underlying mechanism or mechanisms of additional oil recovery X-Ray imaging technology was applied. We have also imaged the end-Point saturations of filled by brine and water core samples. Once the primary drainage is realized we carried out two phases imbibitions: with high salinity brine (waterflooding) and with low salinity brine (tertiary recovery mode). The wettability analysis at pore scale permitted to put in evidence the thermal and saline effects playing a decisive role in rock wettability. We have showed wettability changes are not caused by only electrical double layer expansion, however wettability changes was shown. These changes are explained by wettability transition of second order and observed not only for oil droplet on brine, but also for oil deposited on glass substrate. Finally, the pore space wettability needs to be evidenced at sub-Micrometric scale that is new for the petroleum domain.