An application of neural networks to the prediction of terrestrial wave propagation

Field strength prediction is a central task for the planning of mobile communication systems. The decisive advantage in using neural networks for field strength predictions is given by the possibility of deriving training patterns directly from measurements. This allows the system to become very flexible and adapt to arbitrary environment. Owing to the highly parallel structure of the processing fast prediction systems seem to be possible in the future. First results of a training by measurement data show the feasibility of this approach