Forecasting the ionospheric f0F 2 parameter one hour ahead using a support vector machine technique

Abstract

This paper proposes a method for forecasting the ionospheric critical frequency, f 0F 2, 1 h in advance, using the support vector machine (SVM) approach. The inputs to the SVM network are the time of day, seasonal information, 2 month running mean sunspot number ( R2), 3 day running mean of the 3 h planetary magnetic ap index, the solar zenith angle, the present value f 0F 2( t) and its first and second increments, the observation of f 0F 2 at t−23 h, the 30-day mean value at time, t, f mF 2 ( t) and the previous 30 day running mean of f 0F 2 at t−23 h f mF 2( t−23). The output is the predicted f 0F 2 1 h ahead. The network is trained to use the ionospheric sounding data at Haikou, Guangzhou, Chongqing, Lanzhou, Beijing, Changchun and Manzhouli stations at high and low solar activities. The performance of the SVM model was verified with observed data. It is shown that the predicted f 0F 2 has good agreement with the observed f 0F 2. The performance of the SVM model is superior to that of the autocorrelation and persistence models, and that it is comparable to that of the neural network model.