PREDICTING PERMEABILITY FROM POROSITY USING ARTIFICIAL NEURAL NETWORKS

Permeability values in a borehole are predicted by an artificial neura l network from the porosity values at the same depths. The network use d in this study employs an architecture called backpropagation that is good at making predictions. The traditional approach for permeability prediction is regression analysis. In regression analysis, the relati onship between porosity and permeability is assumed to be known. In re ality, the functional form of this relationship, i.e., the model equat ion, is unknown. In contrast, the neural-network approach assumes no f unctional relationship. Six wells from Big Escambia Creek (Jurassic Sm ackover carbonate) field in southern Alabama were used to test predict ing permeability from porosity using a neural network. Porosity and sp atial data alone were used to predict permeability because these data are readily available from any hydrocarbon field. Three scenarios were performed; in each one, a subset of the six wells was used for a trai ning set, one well for calibration, and one or two wells were used for prediction. For each scenario, simple linear regression was also used to predict permeability from porosity. The neural net predicted perme ability much better than did regression in one scenario; in the other two scenarios the two methods performed equally well. The neural net p redicted permeability accurately using minimal data, but other kinds o f information (e.g., log- or core-derived lithologic information) are easily incorporated if available. In addition, compartmentalization of carbonate reservoirs may be recognizable by this approach.