Multitemporal remote sensing data classification using neural network

In this work a three-layered feedforwrd Neural Netork (NN), trained with the backpropagation algorithm, has been used for classifying a multitemporal Thematic Mapper image. The analisys has been extended to the case where the input data are obtained integrating the satellite image data-set with non Remote Sensed data, as digital elevation data. The aim of the research is to evaluate the effectiveness of a neural network approach with respect to a Maximum Likelihood (ML) statistical one: in order to achieve this goal the ...