Deep Learning for Ionogram Parameter Extraction: A Time-Series Approach to Ionospheric Monitoring

Ionograms provide a direct measurement of the ionosphere’s electron density profile and its irregularities. By examining critical frequencies researchers can identify key parameters—such as the F region critical frequency (foF2), the height of maximum electron density (hmF2), and the presence of Spread F irregularities—that are vital for understanding signal propagation, space weather effects, and radio communication reliability. Over the past decades, tools have been developed for the extraction of ionospheric parameters of ionograms: ARTIST-5 and among others. There are approximations in previous works using deep learning for automatic scaling with parameters extraction of great importance as the identification of the E and F2 layer. These tools generally work for relatively quiet days (QD), but not for days with Spread-F, where a lot of variability is observed in the parameters obtained in those days and manual correction is necessary. In this work, we trained a model combining Convolutional Neuronal Network (CNN), Long Short-Term Memory (LSTM) and Dense layers that can capture the short-term variability of the ionosphere and our model returns the frequency profile. Ionograms were recollected from VIPIR ionosondes, part of the Low-Latitude Ionospheric Sensor Network (LISN). We tested and compared the frequency profiles from our model with manual correction and parameters obtained with ARTIST 5.0 showing significant differences.