Forecasting Spread F at Jicamarca

Spread F is a phenomenon that occurs in the F layer of the Ionosphere and is characterized by plasma depletions. It can have a negative impact on radio communication systems and because of this, it is of interest to develop a model that can predict its occurrence. Radars like digisondes and JULIA (Jicamarca Unattended Long-term Investigations of the Ionosphere and Atmosphere) have observed the Ionosphere at Jicamarca for decades. The datasets that resulted from a collection of these observations joined with geophysical parameters measurements were harnessed to train a Machine Learning model that predicts Spread F. In addition, we compared our model to FIRST (Forecasting Ionospheric Real-time Scintillation Tool) and obtained promising results. Although our model has only been validated with Jicamarca’s dataset it may be used for other longitudes. Furthermore, since the only local measurements used during training were Spread F occurrences and the virtual height of the F layer, the retraining process can easily be done on a single station with an ionosonde receiver.