The performance of Global Navigation Satellite Systems (GNSS) can be highly impacted by the interaction of the radio communication signal with ionized particles in the upper layers of the atmosphere (..
The performance of Global Navigation Satellite Systems (GNSS) can be highly impacted by the interaction of the radio communication signal with ionized particles in the upper layers of the atmosphere (ionosphere). Depending on the shape of the cloud of particles, which is the irregularity, and its speed, the signal can be distorted gravely by intense oscillating signatures called scintillations. Those irregularities and their structures are only understood in-depth for particular events and case studies. In this study, we want to make use of the years of data available for high-rate high magnetic latitude GPS data. To gain a deeper insight into scintillations from multiple sources, we are investigating different machine learning approaches to classify and categorize scintillation events and draw conclusions about physical background processes. For the geomagnetic storm on the 9th of March 2012, we applied a hierarchical clustering analysis on high rate data in phase and power to categorize the temporal scintillation signatures according to their geomagnetic source region. We can distinguish manually selected events from stations inside the polar cap vs those from the auroral oval. From the geomagnetic background data, we are finding input features that will add the most efficiency to our model to detect the scintillation signatures caused by different irregularities and extract those candidate events. Based on this evolving database of events we expect to estimate the importance of the major sources of scintillation in each of the source regions and have a starting point for future studies with CNN and wavelet analysis.