Extending the coverage area of regional ionosphere maps using a support vector machine algorithm

Abstract

Abstract. The coverage of regional ionosphere maps is determined by the distribution of ground-based monitoring stations, e.g., GNSS receivers. Since ionospheric delay has a high spatial correlation, ionosphere map coverage can be extended using spatial extrapolation methods. This paper proposes a support vector machine (SVM) to extrapolate the ionosphere map data with solar and geomagnetic parameters. One year of IGS ionospheric delay map data over South Korea is used to train the SVM algorithm. Subsequently, 1 month of ionospheric delay data outside the input data region is estimated. In addition to solar and geomagnetic environmental parameters, the ionospheric delay data from the inner data region are used to estimate the ionospheric delay data for the outside region. The accuracy evaluation is performed at three levels of range −5, 10, and 15∘ outside the inner data regions. The extrapolation errors are 0.33 TECU (total electron content unit) for the 5∘ region and 1.95 TECU for the 15∘ region. These values are substantially lower than the GPS Klobuchar model error values. Comparison with another machine learning extrapolation method, the neural network, shows a substantial improvement of up to 26.7 %.