Development of machine learning methods for estimating permeability and porosity of oil reservoirs via petro-physical logs

This paper deals with a new model for predicting porosity and permeability of oil reservoirs by coupling a machine learning concept and petrophysical logs. A rigorous machine learning technique called Least Squares Support Vector Machine (LSSVM) was employed. To improve the ability of the LSSVM model a Genetic Algorithm (GA) was employed. The machine learning approach was constructed and tested via data samples recorded from northern Persian Gulf oil reservoirs. Furthermore, other intelligent methods including fuzzy logic, artificial neural network, and hybridized methods were carried out and compared to the proposed GA-LSSVM model. The results gained from the machine learning model proposed here were compared to the relevant real petrophysical data and the outputs achieved from other methods employed in this study. The average relative absolute deviation between the approach …

LSSVM; GA; Permeability