A COMPARATIVE STUDY OF FORECASTING METHODS FOR SPACE WEATHER - CAUSED GNSS POSITIONING PERFORMANCE DEGRADATION

Space weather and ionospheric dynamics have a profound effect on the positioning performance of Global Satellite Navigation System (GNSS). However, the quantification of that effect is still the subject of scientific activities around the world. In the latest contribution to the understanding of the space weather and ionospheric effects on GNSS positioning performance, we conducted a comparative study of several candidates for forecasting method for space weather-induced GNSS positioning performance deterioration. First, a moderately large set of experimentally collected data was established, encompassing space weather and ionospheric activity indices (including: the readings of the Sudden Ionospheric Disturbance (SID) monitors, components of geomagnetic field strength, planetary geomagnetic K (Kp) index, Total Electron Content (TEC), and sunspot number) and observations of GPS positioning error components (northing, easting and height) derived from the International GNSS Service (IGS) reference stations' Receiver Independent Exchange Format (RINEX) files in low solar activity periods. This data set was split into the training and test sub-sets. Then, the selected two supervised machine learning methods (Decision Tree Model - DTM, and Artificial Neural Network - ANN) were applied to the experimentally collected data set in order to establish the appropriate forecasting models for space weather-induced GNSS positioning performance deterioration. The forecasting models were developed in R/rattle statistical programming environment. The forecasting quality of the examined forecasting models was assessed and the conclusions on the advantages and shortcomings of the proposed forecasting models for space weather-caused GNSS positioning performance deterioration were drawn.