Prediction of Surfactant Retention in Porous Media: A Robust Modeling Approach

Demands for hydrocarbon production have been increasing in recent decades. As a tertiary production processes, chemical flooding is one of the effective technologies to increase oil recovery of hydrocarbon reservoirs. Retention of surfactants is one of the key parameters affecting the performance and economy of a chemical flooding process. The main parameters contribute to surfactant retention are mineralogy of rock, surfactant structure, pH, salinity, acidity of the oil, microemulsion viscosity, co-solvent concentration, and mobility. Despite various theoretical studies carried out so far, a comprehensive and reliable predictive model for surfactant retention is still found lacking. In this communication, a mathematical method based on machine learning approach, namely, least square support vector machine modeling is evolved for this purpose. To this end, the model was developed and tested using experimental dynamic surfactant retention data over a wide range of conditions. The results show that the developed model provides predictions in good agreement with experimental retention data. Moreover, it is shown that the developed model is capable of simulating the actual physical trend of surfactant retention versus three most important input parameters: total acid number of oil, pH, and mobility ratio. Finally, for detection of the probable doubtful retention data, outlier diagnosis was performed on the whole data set.