Abstract

Reservoir permeability is a dominant factor in determining reservoir productivity. A new approach for permeability prediction uses a combination of intelligent computing (artificial neural network or ANN) and statistical rock physics with a full utilization of core data, well logs and seismic-derived properties. The integrated method first uses ANN to develop functional transformations from well logs to porosity, followed by seismic-derived acoustic impedance and Poisson's ratio to porosity. Permeability is then simulated throughout the reservoir using the porosity-permeability relationship observed in core analysis. The proposed method is applied to a limestone reservoir in East Java. Validation is carried out by comparing the results to the observed data at well locations as well as by geological justification. The application has shown a potential for supporting reservoir modeling.