Feedback neural networks for ARTIST ionogram processing

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 ƒ0F1 identification that estimates an α angle for the trace segments in the vicinity of the critical frequency ƒ0F1. First results from off‐line tests suggest the potential of implementing new operational autoscaling software in the worldwide Digisonde network.

Recent advances in real-time analysis of ionograms and ionospheric drift measurements with digisondes

“…Promising new techniques for ARTIST have been found (Galkin et al, 1996) but remained initially unclaimed. In recent years the risks of carefree use of autoscaled ionogram data were clearly recognized, and renewed attention was drawn to the ARTIST performance.…”

Extended Analysis of Real‐Time foF2 Mapping in Mideastern China Based On Shortwave Signals

“…Ionospheric reconstruction is a procedure that infers the numerical continuous distribution of f o F 2 within a known area using ionosonde data (Amarante et al, 2005;Chen et al, 2014;Gerzen et al, 2013Gerzen et al, , 2015Stankov et al, 2003). This method is attracting increasing research interest, and many strategies for ionospheric reconstruction have been proposed, including the inversion-distance-weighted interpolation method (Xin et al, 2000), neural network method (Galkin et al, 1996;Ma et al, 2005;Wang et al, 2004), Kriging interpolation method (Chen et al, 2014;Krige, 1951;Minkwitz et al, 2015;Oliver & Webster, 1990;Stanislawska et al, 1996), and utilizing the International Reference Model (IRI-2001) as background ionospheric data to reconstruct f o F 2 (Wang et al, 2006). Among these Radio Science 10.1002/2016RS006161 methods, Kriging is able to accomplish the best linear unbiased prediction of regional variables based on the covariance among variables.…”

Ionospheric electron density profile estimation using commercial AM broadcast signals

“…Groundbased HF radio ionospheric sounding techniques, including vertical sounding, oblique sounding, and oblique backscatter sounding, are still important methods for studying ionospheric electron density profiles. There are hundreds of ionosonde stations around the world that record vertical incidence ionograms day and night, and a significant amount of work has been invested in the automatic calculation of electron density profiles using these ionograms (Galkin et al, 1996, Jiang et al, 2014, Reinisch and Huang, 1982, Reinisch and Huang, 1983, Titheridge, 1985, Zheng et al, 2013.…”