WITHDRAWN: Machine learning methodology for TEC prediction using global positioning system signal measurements

Abstract

Abstract Applications based on the modern Global Navigation Satellite Systems (GNSS) are primarily real-time applications that require high–precision positioning, navigation, and timing information. Propagation of Global Positioning System (GPS) signals through the ionosphere causes delays, allowing opportunities to develop the appropriate ionosphere/space weather nowcast and predict services. The propagation of Global Positioning System (GPS) signals through the ionosphere causes delays, allowing the development of nowcasting and forecasting model for the appropriate ionosphere/space weather services. In view of cosmic meteorological conditions are active (dynamic perturbations), observations of a single ionospheric attribute are not sufficient. Therefore, the accurate model is essential for nowcasting and predicting ionospheric perturbations, considering the effects of space meteorological conditions. Therefore, in this paper describes a new prediction approach, Extreme Kernel–Based Learning Machine (KELM), and introduces new relevance related to ionospheric activity services. The GPS–Total Electron Content (TEC) measurements of Bangalore location (13.02° E and 77.57° N) from 2009 to 2016 were considered for investigation. The outcomes of the proposed approach achieve good forecasting illustration at different seasons and solar period conditions. The error measurements MAE, MAPE, and RMSE, were 0.62, 8.29 and 0.81 TECU (KELM), and 1.44, 14.85, and 1.95 TECU (Auto Regressive Moving Average). With the ability, it would probably be implemented in real–time development applications.