Feedback Neural Networks For Artist Ionogram Processing

Ia Galkin
Bw Reinisch
Ga Ososkov
Eg Zaznobina
Steven P. Neshyba, University of Puget Sound

Abstract

Modern pattern recognition techniques are applied to achieve high quality automatic processing of Digisonde ionograms. An artificial neural network (ANN) was found to be a promising technique for ionospheric echo tracing. A modified rotor model was tested to construct the Hopfield ANN with the mean field theory updating scheme. Tests of the models against various ionospheric data showed that the modified rotor model gives good results where conventional tracing techniques have difficulties. Use of the ANN made it possible to implement a robust scheme of trace interpretation that considers local trace inclination angles available after ANN completes tracing. The interpretation scheme features a new algorithm for f(o)F(1) identification that estimates an alpha angle for the trace segments in the vicinity of the critical frequency f(o)F(1). First results from off-line tests suggest the potential of implementing new operational autoscaling software in the worldwide Digisonde network.