The application of committee Machine with Intelligent Systems to the prediction of permeability from petrographic image analysis and well logs data: a case study from the South Pars gas field, South Iran

Abstract

Permeability is the ability of porous rock to transmit fluids. An accurate knowledge of reservoir permeability is necessary for reservoir management and development. This study presents an improved model based on the integration of petrographic data, conventional logs, and intelligent systems to predict permeability. Petrographic image analysis was employed to measure the optical porosity, pore types, pore morphologies, mineralogy, amount of cement, and type of texture. Available conventional log measurements include bulk density, neutron porosity, and natural gamma ray. The permeability was first predicted using the individual intelligent systems including a neural network (NN), a fuzzy logic (FL), and a neuro-fuzzy (NF) model. Afterwards, two types of committee machine with intelligent systems (CMIS) were used to combine the permeability values calculated from the individual intelligent systems: simple averaging and weighted averaging. In the weighted averaging, a genetic algorithm model was employed to obtain the optimal contribution of each expert. The results show that both of the CMIS performed better than NN, FL, and NF models acting alone.