Title: Application of Machine Learning to Characterization of GPS L1 Ionospheric Amplitude Scintillation
Author(s): Yunxiang (Leo) Liu, Y. Jade Morton, Yu (Joy) Jiao
Published in: Proceedings of IEEE/ION PLANS 2018
April 23 - 26, 2018
Hyatt Regency Hotel
Monterey, CA
Pages: 1159 - 1166
Cite this article: Liu, Yunxiang (Leo), Morton, Y. Jade, Jiao, Yu (Joy), "Application of Machine Learning to Characterization of GPS L1 Ionospheric Amplitude Scintillation," Proceedings of IEEE/ION PLANS 2018, Monterey, CA, April 2018, pp. 1159-1166.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In
Abstract: Ionospheric scintillation refers to the rapid fluctuation of the amplitude and phase of radio-frequency signals, such as GNSS, propagating through the ionosphere. Strong scintillation can severely impact signal acquisition and tracking in a GNSS receiver, resulting in a performance degradation in accuracy and continuity. Therefore, a thorough understanding of ionospheric scintillation effects on GNSS signals has drawn much attention in both the scientific fields and industry. Previously, the scintillation events were manually identified by human experts, which hampers the possibility of conducting a large batch processing. In this paper, we first implement an improved machine learning algorithm to automatically detect scintillation events. We also show that the improved version outperforms the previous implementation. Then we apply the trained machine learning algorithms to a large database of GPS L1C/A data collected in equatorial and high latitude areas to detect amplitude scintillation. Finally, the statistical characterization of the detected amplitude scintillation is presented and discussed.