Smart learning strategy for predicting viscoelastic surfactant (VES) viscosity in oil well matrix acidizing process using a rigorous mathematical approach

Abstract This piece of study attempts to accurately anticipate the apparent viscosity viscoelastic surfactant (VES) based self-diverting acids as a function VES concentration, temperature, shear rate, and pH value. The focus not only is on generating computer-aided models but also developing straightforward reliable explicit mathematical expression. Towards this end, Gene Expression Programming (GEP) used connect aforementioned features target. GEP network trained using wide dataset adopted from open literature leads an empirical correlation for fulfilling aim study. performance proposed model shown be fair enough. accuracy analysis indicates satisfactory Root Mean Square Error R-squared values 7.07 0.95, respectively. Additionally, compared with published correlations established itself superior approach predicting VES-based acids. Accordingly, can potentially served efficient alternative experimental measurements. Its obvious advantages are saving time, lowering expenses, avoiding sophisticated procedures, accelerating diverter design in stimulation operations. Article Highlights evolutionary algorithm modeling Viscoelastic Surfactant-based presents high which demonstrated through multiple analyses. tool expediting phase each operation.