The troposphere refractivity slop determination from propagation loss by the artificial neural networks

The aim of the present paper is to infer the slop of troposphere refractivity, from the measured propagation loss by means of a new artificial neural network structure. The proposed network consists of two cascade neural networks. At first by means of the Hebbian-based maximum eigenfilter, main features of the field at the observation points are extracted. Then the extracted features are fed to a supervised learned neural network (i.e. the multilayer perceptron neural network and/or radial base neural network). The supervised learned neural network is trained to extract the slop of refractivity from the field profile features.