Creating a Database to Identify High-Latitude Scintillation Signatures With Unsupervised Machine Learning

In high latitudes, Global Navigation Satellite System (GNSS) signals experience scintillation due to moving irregularity structures in the ionosphere. These develop as a result of different physical mechanisms, which are as yet principally described on an elementary level for certain storm cases and events. Since there are years of GNSS data available from stations around the globe, we are investigating an unsupervised Machine Learning approach to extract a large variety of groups of scintillation events with similar features. We create a database containing high-rate scintillation events from two geomagnetic storm cases and several stations in the high-latitude region of the Northern hemisphere. By clustering high-rate signatures in signal phase and power according to their major signal characteristics with an agglomerative hierarchical clustering, it is possible to extract different groups of similar types of scintillation signatures. As a result of this study, the database of scintillation signatures in various locations in the auroral oval and polar cap evolves and will be further expanded beyond the storm cases studied in this paper. These can then be linked to the geomagnetic conditions and dynamics in the ionosphere through additional datasets from other instruments, therefore potentially helping us to get a further insight into the ionospheric irregularity physics.