Unlocking the Power of Artificial Intelligence: Accurate Zeta Potential Prediction Using Machine Learning.

Nanoparticles have gained significance in modern science due to their unique characteristics and diverse applications in various fields. Zeta potential is critical in assessing the stability of nanofluids and colloidal systems but measuring it can be time-consuming and challenging. The current research proposes the use of cutting-edge machine learning techniques, including multiple regression analyses (MRAs), support vector machines (SVM), and artificial neural networks (ANNs), to simulate the zeta potential of silica nanofluids and colloidal systems, while accounting for affecting parameters such as nanoparticle size, concentration, pH, temperature, brine salinity, monovalent ion type, and the presence of sand, limestone, or nano-sized fine particles. Zeta potential data from different literature sources were used to develop and train the models using machine learning techniques. Performance indicators were employed to evaluate the models' predictive capabilities. The correlation coefficient (r) for the ANN, SVM, and MRA models was found to be 0.982, 0.997, and 0.68, respectively. The mean absolute percentage error for the ANN model was 5%, whereas, for the MRA and SVM models, it was greater than 25%. ANN models were more accurate than SVM and MRA models at predicting zeta potential, and the trained ANN model achieved an accuracy of over 97% in zeta potential predictions. ANN models are more accurate and faster at predicting zeta potential than conventional methods. The model developed in this research is the first ever to predict the zeta potential of silica nanofluids, dispersed kaolinite, sand-brine system, and coal dispersions considering several influencing parameters. This approach eliminates the need for time-consuming experimentation and provides a highly accurate and rapid prediction method with broad applications across different fields.

Laboratory Investigation of Nanofluid-Assisted Polymer Flooding in Carbonate Reservoirs.

In the petroleum industry, the remaining oil is often extracted using conventional chemical enhanced oil recovery (EOR) techniques, such as polymer flooding. Nanoparticles have also greatly aided EOR, with benefits like wettability alteration and improvements in fluid properties that lead to better oil mobility. However, silica nanoparticles combined with polymers like hydrolyzed polyacrylamide (HPAM) improve polymer flooding performance with better mobility control. The oil displacement and the interaction between the rock and polymer solution are both influenced by this hybrid approach. In this study, we investigated the effectiveness of the injection of nanofluid-polymer as an EOR approach. It has been observed that nanoparticles can change rock wettability, increase polymer viscosity, and decrease polymer retention in carbonate rock. The optimum concentrations for hydrolyzed polyacrylamide (2000 ppm) and 0.1 wt% (1000 ppm) silica nanoparticles were determined through rheology experiments and contact angle measurements. The results of the contact angle measurements revealed that 0.1 wt% silica nanofluid alters the contact angle by 45.6°. The nano-silica/polymer solution resulted in a higher viscosity than the pure polymer solution as measured by rheology experiments. A series of flooding experiments were conducted on oil-wet carbonate core samples in tertiary recovery mode. The maximum incremental oil recovery of 26.88% was obtained by injecting silica nanofluid followed by a nanofluid-assisted polymer solution as an EOR technique. The application of this research will provide new opportunities for hybrid EOR techniques in maximizing oil production from depleted high-temperature and high-salinity carbonate reservoirs.

Fine Migration Control in Sandstones: Surface Force Analysis and Application of DLVO Theory.

Formation damage caused by fine migration and straining is a well-documented phenomenon in sandstone reservoirs. Fine migration and the associated permeability decline have been observed in various experimental studies, and this phenomenon has been broadly explained by the analysis of surface forces between fines and sand grains. The Derjaguin-Landau-Verwey-Overbeek (DLVO) theory is a useful tool to help understand and model the fine release, migration, and control phenomena within porous media by quantifying the total interaction energy of the fine-brine-rock (FBR) system. Fine migration is mainly caused by changes in the attractive and repulsive surface forces, which are triggered by mud invasion during drilling activity, the utilization of completion fluid, acidizing treatment, and water injection into the reservoir during secondary and tertiary recovery operations. Increasing pH and decreasing water salinity collectively affect the attractive and repulsive forces and, at a specific value of pH, and critical salt concentration (CSC), the total interaction energy of the FBR system (V T) shifts from negative to positive, indicating the initiation of fine release. Maintaining the system pH, setting the salinity above the CSC, tuning the ionic composition of injected water, and using nanoparticles (NPs) are practical options to control fine migration. DLVO modeling elucidates the total interaction energy between fines and sand grains based on the calculation of surface forces of the system. In this context, zeta potential is an important indicator of an increase or decrease in repulsive forces. Using available data, two correlations have been developed to calculate the zeta potential for sandstone reservoirs in high- and low-salinity environments and validated with experimental values. Based on surface force analysis, the CSC is predicted by the DLVO model; it is in close agreement with the experimental value from the literature. The critical pH value is also estimated for alkaline flooding. Model results confirm that the application of NPs and the presence of divalent ions increase the attractive force and help to mitigate the fine migration problem. Hence, a new insight into the analysis of quantified surface forces is presented in current research work by the practical application of the DLVO theory to model fine migration initiation under the influence of injection water chemistry.

Effects of chelating agents on heavy metals in Hepatitis C Virus (HCV) patients.

Heavy metals are released into the environment through both human and natural sources, may have a direct hepatic toxicity and are involved in chronic liver diseases. Modification in the regulation of heavy metals metabolism enhanced hepatitis c virus (HCV) replication which ultimately reduced outcomes of anti-viral therapy in chronic HCV patients. Chelation therapy with new drugs seems to eradicate HCV and may prevent liver complications. The present study was planned to explore the effects of MiADMSA (lipophilic chelating agent) for achieving maximum heavy metals elimination in hepatitis c virus patients with minimum side effects. For this purpose concentration of heavy metal was determined in HCV patients and established correlation of heavy metals between healthy persons and HCV patients. Atomic absorption spectrophotometer (AAS) was used to explore them. Concentrations of heavy metal in different samples (blood serum, nails and hair) of patients and healthy individuals. Result revealed that heavy metals (Lead, Cobalt, Cadmium, Manganese, Iron and Cooper) concentration were significantly higher in blood of HCV patients as compared to normal persons, but some metals like Ni and Zn were present in normal concentration and in low concentration respectively. After chelation with monoisoamyl DMSA (MiADMSA) a significant amount of heavy metals was excreted in the urine in a dose dependent manner. It was generally observed from the results that TDS is a better treatment option than BD for chelation of heavy metals in hepatitis c virus patients. This chelation therapy will be helpful to reverse the HCV related health problems.