Modeling and Forecasting Ionospheric foF2 Variation in the Low Latitude Region during Low and High Solar Activity Years

Prediction of ionospheric parameters, such as F2 layer critical frequency (foF2) at low latitude regions is significant interest in understanding variation effects on high-frequency communication and global navigation satellite system. Currently, deep learning algorithms have made a striking accomplishment capturing variability. In this paper, we use the state-of-the-art hybrid neural network combined with quantile mechanism to predict foF2 parameter variations under high solar activity years (solar cycle-24) space weather events. The composed convolutional (CNN) bidirectional long short-term memory (BiLSTM), which CNN BiLSTM networks extracted spatial temporal features variation, respectively. proposed method was trained tested 5 (2009–2014) observation data from Advanced Digital Ionosonde located Brisbane, Australia (27°53′S, 152°92′E). It evident results that model performs better than International Reference Ionosphere 2016 (IRI-2016), (LSTM), prediction models. extensively captured feature, predicted it two events (29 September 2011 22 July 2012).