The accurate determination of key parameters, including the CO₂-hydrocarbon solubility ratio (Rs), interfacial tension (IFT), and minimum miscibility pressure (MMP), is vital for the success of CO₂-enhanced oil recovery (CO₂-EOR) projects. This study presents a robust machine learning framework that leverages deep neural networks (MLP-Adam), support vector regression (SVR-RBF) and extreme gradient boosting (XGBoost) algorithms to obtained accurate predictions of these critical parameters. The models are developed and validated using a comprehensive database compiled from previously published studies. Additionally, an in-depth analysis of various factors influencing the Rs, IFT, and MMP is conducted to enhance our understanding of their impacts. Compared to existing correlations and alternative machine learning models, our proposed framework not only exhibits lower calculation errors but also provides enhanced insights into the relationships among the influencing factors. The performance evaluation of the models using statistical indicators revealed impressive coefficients of determination of unseen data (0.9807 for dead oil solubility, 0.9835 for live oil solubility, 0.9931 for CO₂-n-Alkane interfacial tension, and 0.9648 for minimum miscibility pressure). One notable advantage of our models is their ability to predict values while accommodating a wide range of inputs swiftly and accurately beyond the limitations of common correlations. The dataset employed in our study encompasses diverse data, spanning from heptane (C₇) to eicosane (C₂₀) in the IFT dataset, and MMP values ranging from 870 psi to 5500 psi, covering the entire application range of CO₂-EOR. This innovative and robust approach presents a powerful tool for predicting crucial parameters in CO₂-EOR projects, delivering superior accuracy, speed, and data diversity compared to those of the existing methods.

Tight reservoirs around the world contain a significant volume of hydrocarbons; however, the heterogeneity of these reservoirs limits the recovery of the original oil in place to less than 20%. Accurate characterization is therefore needed to understand variations in reservoir properties and their effects on production. Water saturation (Sw) has always been challenging to estimate in ultra-tight reservoirs such as the Bakken Formation due to the inaccuracy of resistivity-based methods. While machine learning (ML) has proven to be a powerful tool for predicting rock properties in many tight formations, few studies have been conducted in reservoirs of similar complexity to the Bakken Formation, which is an ultra-tight, multimineral, low-resistivity reservoir. This study presents a workflow for Sw prediction using well logs, core data, and ML algorithms. Logs and core data were gathered from 29 wells drilled in the Bakken Formation. Due to the inaccuracy and lack of robustness of the tried and tested regression models (e.g., linear regression, random forest regression) in predicting Sw as a continuous variable, the problem was reformulated as a classification task. Instead of exact values, the Sw predictions were made in intervals of 10% increments representing 10 classes from 0% to 100%. Gradient boosting and random forest classifiers scored the best classification accuracy, and these two models were used to construct a voting classifier that achieved the best accuracy of 85.53%. The ML model achieved much better accuracy than conventional resistivity-based methods. By conducting this study, we aim to develop a new workflow to improve the prediction of Sw in reservoirs where conventional methods have poor performance.

Multi-stage hydraulic fracturing (MsHF) is the main technology to improve hydrocarbon recovery from shale plays. Associated with their rich organic contents and laminated depositional environments, shales exhibit transverse isotropic (TI) characteristics. In several cases, the lamination planes are horizontal in shale formations with a symmetric axis that are vertical to the bedding plane; hence, shale formations are known as transverse isotropic vertical (TIV) rocks. Ignoring the TIV nature of shale formations leads to erroneous estimates of in situ stresses and consequently to inefficient designs of fractural geometry, which negatively affects the ultimate recovery. The goal of this study is to investigate the effects of TIV medium characteristics on fractural geometry, spacing, and stress shadow development in the Jurassic Tuwaiq Mountain formation (TMF) in the Jafurah basin, which is a potential unconventional world-class play. This formation is the main source for prolific Jurassic oil reservoirs in Saudi Arabia. On the basis of a petrophysical evaluation in the Jafurah basin, TMF exhibited exceptional unconventional gas characteristics, such as high total organic content (TOC) and low clay content, and it was in the proper maturity window for oil and gas generation. The unconventional Jafurah field covers a large area that is comparable to the size of the Eagle Ford shale play in South Texas, and it is planned for development through multi-stage hydraulic fracturing technology. In this study, analytical modeling was performed to estimate the fractural geometry and in situ stresses in the anisotropic medium. The results show that the Young’s modulus anisotropy had a noticeable impact on fractural width, whereas the impact of Poisson’s ratio was minimal. Moreover, we investigated the impact of stress anisotropy and other rock properties on the stress shadow, and found that a large stress anisotropy could result in fractures being positioned close to one another or theoretically without minimal fractural spacing concerns. Additionally, we estimated the fractural aspect ratio in different propagation regimes and observed that the highest aspect ratio had occurred in the fractural toughness-dominated regime. This study also compares the elastic properties and confirms that TMF exhibited greater anisotropic properties than those of Eagle Ford. These findings have practical implications for field operations, particularly with regard to the fractural geometry and proppant placement.

Organic-rich mud rocks are being developed on a large scale worldwide, including in the Middle East. The Jurassic Tuwaiq Mountain Formation (TMF) in the Jafurah Basin is a potential world-class unconventional play. Based on a petrophysical evaluation of the Jafurah basin, the TMF exhibits exceptional and unconventional gas characteristics, such as a high total organic content (TOC) and low clay content. Additionally, the TMF is in the appropriate maturity window, indicating that it has reached the required level of thermal maturity to generate hydrocarbons. Plans for the development of the Jafurah unconventional field use multistage hydraulic fracturing technology. The elastic properties of the shale formation, particularly its Young’s modulus and Poisson’s ratio, dictate how the rock responds to stress and deformation. These properties strongly impact the growth of hydraulic fractures in shale formations. Without a comprehensive understanding of the elastic properties, predicting the bulk mechanical response of the target zones and surrounding layers would be challenging. Therefore, this study aims to predict the elastic characteristics of the Jafurah shale play considering the variations in carbonate facies, the kerogen volume fraction, and the pore’s geometry. Petrophysical and XRD data were used to estimate the elastic properties of various tiers (geological units) of the TMF (Tiers 1, 2, and 3). Inclusion-based, differential effective medium (DEM) rock physics models were used to estimate the formation’s elastic and velocity properties as a function of the kerogen volume fraction and the pore’s geometry. The results showed that the Young’s modulus as well as the mineral and elastic brittleness indices increase as the volume fraction of calcite increases. At the same time, they decrease due to intensified clay and kerogen volumes. The effect of the TMF’s elastic parameters on the rock brittleness behavior was also investigated by considering the formation’s mineralogy, as well as clay and kerogen contents. The results led to the development of physics-based correlations of the mineral brittleness index as function of the Young’s modulus and Poisson’s ratio for various tiers of the TMF.