Comparison of the Performance of the Regression Models in GPS-Total Electron Content Prediction

Abstract

The ionosphere is an important layer that provides radio communication in the upper atmosphere. The ionosphere is located between 50 km and 1000 km above the atmosphere. Electron density, which is the most important parameter of the ionosphere, changes depending on location, time, seasons, altitude, solar, geomagnetic and seismic activity. A significant measurable amount of electron density is Total Electron Content (TEC), which is used to probe the structure of the ionosphere and upper atmosphere. The Global Positioning System (GPS), which has a low cost and widespread receiver network is prominent used in TEC estimation. The IONOLAB-TEC data estimated from GPS is used in this study. Prediction of TEC is important phenomenon to operate and to plan the Earth-space and satellite-to-satellite communication systems, to generate the earthquake precursor signals using TEC and to detect of anomalies in the ionosphere. In this study, IONOLAB-TEC data obtained from GPS is estimated using regression models. Among the tested algorithms, it is observed that the Exponential Gaussian Process Regression and Interactions Linear Regression algorithms are very successful and high-performance models for TEC estimation.