Application of convolution neural networks for critical frequency fₒF2 prediction
Journal Title: Solar-Terrestrial Physics - Year 2023, Vol 9, Issue 1
Abstract
Ionosphere has an important impact on the quality of radio communication, radar, and global positioning. One of the essential characteristics describing the state of the ionosphere is its critical frequency fₒF2. Its prediction provides effective modes of operation of technical radio equipment as well as enables calculation of the corrections needed to improve the accuracy of its functioning. Different physical and empirical models are generally used for fₒF2 prediction. This paper proposes an empirical prediction technique based on machine learning methods and observational history. It relies on a regression approach to the prediction based on the known daily quasi-periodicity of ionospheric parameters related to solar illumination. Algorithmically, this approach is implemented in the form of convolutional neural networks with two-dimensional convolution. The input data for the analysis is presented as two-dimensional solar time — date matrices. The model was trained on data from the mid-latitude ionosonde in Irkutsk (RF) and tested using data from several mid-latitude ionosondes: Arti (RF), Warsaw (Poland), Mohe (China). It is shown that the main contribution to the prediction value of fₒF2 is made by the data on the nearest few days before the prediction; the contribution of the remaining days strongly decreases. This model has the following forecast quality metrics (Pearson correlation coefficient 0.928, root mean square error 0.598 MHz, mean absolute error in percent 10.45 %, coefficient of determination 0.861) and can be applied to fₒF2 forecast in middle latitudes.
Authors and Affiliations
Salimov B. G. , Berngardt O. I. , Hmelnov A. E. , Ratovsky K. G. , Kusonsky O. A.
Keywords
Related Articles
- EP ID EP714643
- DOI 10.12737/stp-91202307
- Views 59
- Downloads 0
Studying the small-scale structure of a polarization jet during the April 20, 2018 geomagnetic storm
In this work, we study the small-scale structure of a polarization jet in the subauroral region during the April 20, 2018 geomagnetic storm. We report measurement results of plasma parameters inside the polarization jet...
Long-term variations in peak electron density and temperature of mesopause region: Dependence on solar, geomagnetic, and atmospheric activities, long-term trends
The paper overviews the main results of the study of long-term variations in characteristics of the upper neutral atmosphere and ionosphere, obtained during the implementation of Russian Science Foundation Project No. 22...
STUDYING THE RELATIONSHIP OF LOCALIZATION PARAMETERS OF SOLAR SOURCES OF MAGNETIC CLOUDS WITH THEIR CHARACTERISTICS AND SUBSTORM ACTIVITY
We propose a method for determining location and orientation of extended solar sources of magnetic clouds, using coronagraph data and SOHO EIT/MDI images of the photosphere. To estimate the probability of formation of ma...
BEHAVIOR OF ELECTRON DENSITY IN THE IONOSPHERE OVER NORILSK DURING THE PERIOD OF DECLINING SOLAR ACTIVITY
We report the results of approximation of electron density Ne array obtained with a digisonde at the high-latitude station Norilsk (69.40° N, 88.10° E) during years of declining solar activity (2003–2006). The calculatio...
Observation at radio frequencies of the hydroxyl (OH) absorption line in filaments and prominences above active regions of the Sun
When observing the Sun with RATAN-600 radio telescope using a spectropolarimetric complex in the range 1–3 GHz, as well as when observing coronal rain, absorption in the radio emission was discovered in the spectral regi...