Relationship of permeability, porosity and depth using an artificial neural network

Characterizing rock permeability and its special distribution in a heterogeneous reservoir is a problem with no direct known solution. To date, investigators have tried to find parametric correlation between different direct measurable parameters such as porosity, depth and permeability. However, due to complex nature of the phenomena, the proposed correlations are not accurate and reliable. Attempts are made to utilize artificial neural networks (ANNs) for identification of the relationship, which may exist between permeability, porosity and depth of a reservoir. The radial basis function (RBF) neural network architecture has been used successfully in predicting the permeability of a typical Iranian oilfield rock.