Petrophysical properties determination of tight gas sands from NMR data using artificial neural network

Analysis of heterogeneous gas sand reservoirs is one of the most difficult problems. These reservoirs usually produce from multiple layers with different petrophysical properties. Therefore, using new well logging techniques like NMR or a combination of NMR and conventional open hole logs is 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 focuses on permeability estimation from NMR logging data. Three models have been used to derive permeability from NMR; Kenyon model, Coates-Timer model and Bulk Gas Magnetic Resonance model. These models have advantages and limitations which depend on the reservoir characteristics. We first estimated permeability from NMR data using the Bulk Gas model. Then neural network model was developed to predict formation permeability using NMR and other open hole logs data. The permeability results of the neural network model and the Bulk Gas model were validated by core permeability for the studied wells.