Permeability Prediction Based on Hydraulic Flow Units (HFUs) and Adaptive Neuro-fuzzy Inference Systems (ANFIS) in an Iranian Southern Oilfield

An accurate description of reservoir is necessary for reservoir simulation and performance prediction. It goes without saying that permeability and porosity are two important fundamental parameters to be known for reservoir characterization. Since it is not conceivable to perform coring operation for any place in a reservoir because of cost and time, different methodologies have been introduced to calculate these parameters from different well logs that are usually available for every well in a reservoir. Hydraulic flow unit (HFU) is one of the practical methods in reservoir simulation. HFU is defined as volume of rock that according to petrophysical and geological properties has similar flow of fluid. The concept of HFU has been developed to integrate geological and petroleum engineering data to estimate permeability in cored zone and then use their result to uncored zone. For estimation of HFUs there are some approaches according to data available that some of these methods are gamma ray, flow zone indicator, cumulative flow and storage capacity curve, and stratigrafic modified Lorenz plot. Computational intelligences are another approach that be used to estimate permeability and porosity in cored zone and related the results to uncored zone. Fuzzy logic, genetic algorithm, artificial neural network, and adaptive neuro-fuzzy inference systems (ANFIS) are some kind of computational intelligences. The authors used ANFIS and HFU models to estimate permeability in a southern Iranian oilfield.