Recent news
Selection of anomalies in ionospheric parameters on the basis of combination of multiscale wavelet-decomposition and neural networks
- Institute of Cosmophysical Researches and Radio Wave Propagation FEB RAS, Russia
- Kamchatka State Technical University, Russia
The authors propose a method for the analysis of critical frequency
parameters of the ionospheric layer F2, based on the combination of
multiscale analysis and multilayer neural networks, which allows us to
distinguish the abnormal features of ionosphere behavior. The complexity
of solving the problems of ionospheric parameter processing and analysis
is associated with their complex structure. They include a large number of
components, contain local features of various shapes and duration,
anomalous effects and noise factors. Traditional approaches and methods
for ionospheric parameter analysis based on the smoothing procedure, lead
to distortion and information loss. One of the major drawbacks of these
methods is the lack of effective means for adaptation to the complex
time-dependent data structure. The proposed method is based on the
representation of the recorded time series of foF2 in the form of
different scale components and their approximation by adaptive neural
networks of variable structure. The method, algorithm and software,
developed on its basis, allow us to perform a detailed analysis of each
component and to distinguish anomalies that appear during increased
seismic activity in Kamchatka. We used the recorded data of foF2 for the
period 1969-2010. (''Paratunka'' station, Kamchatka). Comparison of the
results of the ionospheric parameter processing with the Catalog of
earthquakes and geomagnetic data showed the efficiency of the proposed
method, and allowed us to allocate periods of anomalous behavior of the
ionosphere.