Empirical transfer function determination by the use of multilayer perceptron

Neural Networks are relevant statistical methods to extract information fro m data when physical phenomena are very complicated and cannot be described in terms of theoretical analysis. Scatterometers are active microwave rada r which accurately measure the power of the backscatter signal versus incid ent signal in order to calculate the normalized radar cross section (a,) of the ocean surface. We use multilayer perceptrons in order to determine the Geophysical Model Function and to estimate the variability of the signal o f ERS-1, ERS-2 and NSCAT scatterometers. (C) 2000 Published by Elsevier Sci ence B.V. All rights reserved.