| Prediction of Ionospheric Scintillation by Combination of Neural Network and Genetic Algorithm using Space Geodetic Data |
| Paper ID : 1061-SMPR |
| Authors: |
|
Alireza Atabati *1, M.Mahdi Alizadeh2, Harald Schuh3 1Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran – Iran 21. Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran – Iran 2. Institute of Geodesy and Geoinformation Sciences, Technical University of Berlin, Germany 31. Institute of Geodesy and Geoinformation Sciences, Technical University of Berlin, Germany 2. German Research Centre for Geosciences GFZ, Potsdam, Germany |
| Abstract: |
| The ionospheric plasma bubbles can cause unpredictable changes in the ionospheric electron density. These variations in the ionospheric layer generate a phenomenon known as the ionospheric scintillation. Ionospheric scintillation could affect the phase and amplitude of the radio signals traveling through this medium. This phenomenon frequently occurs around the magnetic equator, in the low latitudes as well as in the high latitude regions. Patterns of ionospheric scintillation occurrence are dependent on spatiotemporal ionospheric variabilities. In this study, we implement the Artificial Neural Network (ANN) technique for detecting ionospheric scintillation. ANN is a data-dependent method that its performance improves with the sample size. Due to the advantages of ANN for large datasets and noisy data, the ANN model has been implemented for predicting the occurrences of amplitude scintillations. In this paper, the Genetic Algorithm (GA) technique is considered to obtain primary weights of the ANN model. This procedure is applied to GPS observations at GUAM station (Latitude: 144.8683, Longitude: 13.5893) in order to predict appropriate S4 values. The modeling was carried out for the whole month of June 2017. This model along with ionospheric physical data was used for predicting ionospheric scintillation on the first day of July 2017. The designed model can predict daily ionospheric scintillation with the accuracy of about 86%. |
| Keywords: |
| Global Positioning System, Ionospheric Scintillation, Artificial Neural Network, Genetic Algorithm |
| Status : Paper Accepted (Poster Presentation) |
