Permeability values in a borehole are predicted by an artificial neural network from the porosity values at the same depths. The network used 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 relationship between porosity and permeability is assumed to be known. In reality, the functional form of this relationship, i.e., the model equation, is unknown. In contrast, the neural-network approach assumes no functional relationship.

Six wells from Big Escambia Creek (Jurassic Smackover carbonate) field in southern Alabama were used to test predicting permeability from porosity using a neural network. Porosity and spatial 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 training 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 permeability much better than did regression in one scenario; in the other two scenarios the two methods performed equally well. The neural net predicted permeability accurately using minimal da a, but other kinds of 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.