DETERMINATION OF POROSITY AND PERMEABILITY IN RESERVOIR INTERVALS BY ARTIFICIAL NEURAL-NETWORK MODELING, OFFSHORE EASTERN CANADA

A quantitative integration of porosity/permeability measurements and w ell log data from the major reservoir intervals throughout the basin i s carried out using a back-propagation artificial neural network (BP-A NN), modified with the Marquardt algorithm. After data preprocessing a nd training/supervising example preparation, a model for the relations hip among porosity, permeability and well log responses was establishe d with the BP-ANN technique. The BP-ANN model was then used to constru ct profiles of porosity and permeability in both cored and uncored wel ls for the Avalon, Hibernia and Jeanne d'Arc formations from well logs . The BP-ANN derived porosity and permeability curves provide a basis for further reservoir studies, such as inter-well permeable units reco gnition and correlation, and basin-wide reservoir quality evaluation.