Search

This study employs a stacked ensemble machine learning approach to predict carbonate rocks' porosity and absolute permeability with various pore-throat distributions and heterogeneity. Our dataset consists of 2D slices from 3D micro-CT images of four carbonate core samples. The stacking ensemble learning approach integrates predictions from several machine learning-based models into a single meta-learner model to accelerate the prediction and improve the model's generalizability. We used the randomized search algorithm to attain optimal hyperparameters for each model by scanning over a vast hyperparameter space. To extract features from the 2D image slices, we applied the watershed-scikit-image technique. We showed that the stacked model algorithm effectively predicts the rock's porosity and absolute permeability. [ABSTRACT FROM AUTHOR]

The Darcy-scale properties of reservoir rocks, such as capillary pressure and relative permeability, are controlled by multiphase flow properties at the pore scale. In the present paper, we implement a volume of fluid (VOF) method coupled with a physically based dynamic contact angle to perform pore-scale simulation of two-phase flow within a porous medium. The numerical model is based on the resolution of the Navier–Stokes equations as well as a phase fraction equation incorporating a dynamic contact angle model with wetting hysteresis effect. After the model is validated for a single phase, a two-phase flow simulation is performed on both a Newtonian and a non-Newtonian fluid; the latter consists of a polymer solution displaying a shear-thinning power law viscosity. To investigate the effects of contact angle hysteresis and the non-Newtonian nature of the fluid, simulations of both drainage and imbibition are carried out in order to analyze water and oil saturation—particularly critical parameters such as initial water saturation ( S w i ) and residual oil saturation ( S o r ) are assessed in terms of wettability. Additionally, the model sensitivities to the consistency factor (χ), the flow behavior index (n), and the advancing and receding contact angles are tested. Interestingly, the model correctly retrieves the variation in S o r and wettability and predicts behavior over a wide range of contact angles that are difficult to probe experimentally. [ABSTRACT FROM AUTHOR]

Several benefits of low salinity/engineered water injection (LSWI/EWI) have been reported in the literature including its ability to increase oil recovery at low cost and with least environmental impact. Nevertheless, the related reservoir-engineering problems to this technique such as formation damage is still uncertain and has not been thoroughly investigated. This study investigates the effect of water composition on formation damage and the related oil recovery from a geochemical prospective. The study presents coupling of the IPhreeqc geochemical engine with Matlab to simultaneously solve the oil-water multiphase flow in 1-D and the related geochemical reactions. Using this coupling technique, the geochemical capabilities of Phreeqc were successfully incorporated in a multiphase flow simulator. The latter enabled modeling of reactive transport and formation damage in subsurface multiphase reservoir. The developed model was validated against single phase geochemical simulator, analytical solution of Buckley-Leverette equation, commercial reservoir engineering simulator, and experimental data. The results showed that the temperature, sulfate concentration, and dilution of injection water have a pronounced effect on formation dissolution and precipitation during LSWI/EWI. Also, anhydride scale is the main controlling solid specie for formation damage in the investigated case study. In addition, high temperature water injection should be avoided in carbonate reservoirs due to the likelihood of anhydride precipitation and formation damage. This precipitation occurs because of the low-solubility of anhydride at high temperature. Moreover, water dilution could decrease scale formation while sulfate spiking might increase anhydride precipitation. Hence, sulfate concentration should be optimized as a wettability alteration agent to enhance oil recovery while avoid formation damage. Furthermore, as a sequence of anhydride precipitation by sulfate spiking, oil production is expected to decrease by around 10% in the selected case study. The dissolution and precipitation mechanisms during LSWI/EWI are very case-dependent and hence, the findings of this study cannot be generalized. • One of the few papers on formation damage effect on oil recovery by low salinity/engineered water injection (LSWI/EWI). • Water composition effect on formation damage and related oil recovery was predicted from a geochemical aspect using coupled Matlab-IPhreeqc simulator.. • Temperature, sulfate concentration, and dilution of injection water have a pronounced effect on formation dissolution and precipitation during LSWI/EWI.. • Anhydrite scale is the main controlling solid specie of formation damage for this case study.. • Sulfate concentration should be optimized as a wettability alteration agent to enhance oil recovery while avoid formation damage.. • Formation damage by LSWI/EWI and the related effect on oil recovery is very case-dependent and hence, the findings of this study cannot be generalized.. [ABSTRACT FROM AUTHOR]

Polymer flooding is a well-established enhanced oil recovery (EOR) technique for mobility control. However, several factors affect a successful application of polymer at field-scale including injectivity and retention. The latter two parameters can lead to poor polymer performance. This work investigates the flow behavior of an ATBS-based polymer in carbonate reservoirs under high-temperature and high-salinity (HTHS) conditions. Formation water sample as well as three carbonate cores were utilized in this work. Rheological studies and injectivity tests were conducted on the polymer at two different temperatures of 25 °C and 90 °C. Polymer dynamic retention tests were also conducted to assess polymer loss in porous media. The results showed that the polymer has a good tolerance to salinity with a shear thickening behavior within the injected flow rates under temperature condition of 25 °C. The in-situ rheological studies also showed that this viscoelastic behavior disappears at higher temperatures of 90 °C. From injectivity tests, with increasing flow rate, resistance factor increases at 25 °C and decreases at 90 °C, which is related to polymer rheological behavior and in particular in-situ viscosity. In addition, resistance factor at 90 °C was lower than that of 25 °C due to the decrease in polymer retention as temperature increases. The paper provides more insight into the applicability of an ATBS-based polymer in reservoirs under harsh conditions. The study also helps in better understanding polymer flow behavior for designing successful field projects. • This work investigates the flow behavior of an ATBS-based polymer under harsh carbonate reservoirs conditions. • Injectivity experiments were conducted to investigate injectivity and retention of the polymer at 25 °C and 90 °C. • The polymer showed good salinity tolerance with a shear thickening behavior at well flow rates under temperature of 25 °C. • The shear thickening behavior disappeared under high temperature of 90 °C. [ABSTRACT FROM AUTHOR]

Carbon dioxide foam injection is a promising enhanced oil recovery (EOR) method, being at the same time an efficient carbon storage technology. The strength of CO 2 foam under reservoir conditions plays a crucial role in predicting the EOR and sequestration performance, yet, controlling the strength of the foam is challenging due to the complex physics of foams and their sensitivity to operational conditions and reservoir parameters. Data-driven approaches for complex fluids such as foams can be an alternative method to the time-consuming experimental and conventional modeling techniques, which often fail to accurately describe the effect of all important related parameters. In this study, machine learning (ML) models were constructed to predict the oil-free CO 2 foam apparent viscosity in the bulk phase and sandstone formations. Based on previous experimental data on various operational and reservoir conditions, predictive models were developed by employing six ML algorithms. Among the applied algorithms, neural network algorithms provided the most precise predictions for bulk and porous media. The established models were then used to compute the critical foam quality under different conditions and determine the maximum apparent foam viscosity, effectively controlling CO 2 mobility to co-optimize EOR and CO 2 sequestration., Competing Interests: There are no conflicts to declare., (This journal is © The Royal Society of Chemistry.)