A data-driven model to estimate the pore volume to breakthrough for carbonate acidizing

Abstract

AbstractThis research investigates the impact of different rock, acid, and reaction dynamic properties on the pore volume to breakthough (PVBT) at different acid injection rates using in-house developed two-scale continuum simulation model. We analyzed the parameters relation and developed a reliable machine learning model to accurately predict the PVBT at similar range of investigated parameters. In the simulation, it was found that different acid concentrations result in the same optimum injection velocity but at large contrast in PVBT between low and high acid concentration. However, other parameters such as diffusion coefficient and reaction rate exhibited an inverse PVBT behavior across optimum injection velocity due to change in acid transport and reaction behavior. After that, different reliable machine learning algorithms were employed to predict the optimum PVBT for carbonates matrix acidizing. The utilized machine learning models undergone multiple optimizations and comparison to obtain the most accurate prediction performance. The artificial neural network model with 2 hidden layers outperforms the other optimizations with 11.27% estimation error, 0.96 R2and 0.98 correlation coefficient for the testing data set. Finally, an empirical correlation was developed to accurately estimate PVBT at a low cost and very short time compared to lab experiments and numerical simulation models. The novelty of this research stems from examining PVBT curves behavior by varying five matrix acidizing parameters independently, analyzing the correlation between these parameters and developing machine learning model for handy and reliable optimum PVBT estimation.