Application of the radial basis function neural network to the prediction of log properties from seismic attributes
Brian H. Russell, Laurence R. Lines, Daniel P. Hampson
In this paper, we use the radial basis function neural network, or RBFN, to predict reservoir log properties from seismic attributes. We also compare the results of this approach with the use of the generalized regression neural network, GRNN, for the same problem, as proposed by Hampson et al (2001). We discuss both the theory behind these methods and the methodology involved in applying neural networks to seismic attributes. We then illustrate the method using the Blackfoot 3D seismic volume, a channel sand example from Alberta.