Neural Permeability Prediction of Heterogeneous Gas Sand Reservoirs

Abstract

Analysis of heterogeneous gas sand reservoirs is one of the most difficult problems. These reservoirs usually produced from multiple layers with different permeability and complex formation, which is often enhanced by natural fracturing. Therefore, using new well logging techniques like NMR or a combination of NMR and conventional open hole logs, as well as developing new interpretation methodologies are essential for improved reservoir characterization. Nuclear magnetic resonance (NMR) logs differ from conventional neutron, density, sonic and resistivity logs because the NMR measurements provide mainly lithology independent detailed porosity and offer a good evaluation of the hydrocarbon potential. NMR logs can also be used to determine formation permeability and capillary pressure. This paper concentrates on permeability estimation from NMR logging parameters. Three models used to derive permeability from NMR are Kenyon model, Coates-Timer model and Bulk Gas Magnetic Resonance model. These models have their advantages and limitations depending on the nature of reservoir properties. This paper discusses permeability derived from Bulk Gas Magnetic Resonance Model and introduces neural network model to derive formation permeability using data from NMR and other open hole log data. The permeability results of neural network model and other models were validated by core permeability for the studied wells.