Abstract
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.