Automatic detection of ionospheric scintillation‐like GNSS satellite oscillator anomaly using a machine‐learning algorithm

Abstract

In this paper, we propose a machine‐learning‐based approach to automatically detect a satellite oscillator anomaly. A major challenge is to differentiate an oscillator anomaly from ionospheric scintillation. Although both scintillation and oscillator anomalies cause phase disturbances, their underlying physics are different and, therefore, show different carrier‐frequency dependency. By using triple‐frequency signals, distinct features are extracted from the disturbed signals and applied to the radial basis function (RBF) support vector machine (SVM) classifier to identify an oscillator anomaly. The results show that the proposed RBF SVM displays superior performance and outperforms several other classification methods. The proposed approach is applied to an extensive GNSS database to conduct automatic satellite oscillator anomaly detection. Preliminary detection results validate the effectiveness of the proposed method. On average, one‐to‐three satellite oscillator anomaly events are detected daily at each receiver location.

Machine Learning Prediction of Storm‐Time High‐Latitude Ionospheric Irregularities From GNSS‐Derived ROTI Maps

“…The studies above either focused on individual GNSS receiver locations (De Lima et al., 2015; Lamb et al., 2019; Prikryl et al., 2012) or treat the scintillation forecasting as a classification problem (Linty et al., 2018; Y. Liu & Morton, 2020; McGranaghan et al., 2018). In this study, we present an image‐based machine learning algorithm to forecast the magnitude of ionospheric irregularities.…”

“…The studies above either focused on individual GNSS receiver locations (De Lima et al, 2015;Lamb et al, 2019;Prikryl et al, 2012) or treat the scintillation forecasting as a classification problem (Linty et al, 2018;Y. Liu & Morton, 2020;McGranaghan et al, 2018).…”

Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine Learning Algorithm

“…Satellite oscillator anomalies have been investigated in several past studies (e.g., Benton andMitchell [2012, 2014], Liu and Morton [2020b]). Benton and Mitchell (2012) observed pulses of rapid phase variations at GPS L1 caused by a satellite oscillator anomaly.…”

“…In Benton and Mitchell (2014), a modern GPS Block IIF satellite (PRN 1) showed sequences of oscillator anomalies (with a maximum phase deviation larger than one cycle) on October 26, 2012. In Liu and Morton (2020b), frequent micro satellite oscillator anomalies (with a maximum phase deviation around 0.2 cycles) were observed from multiple GPS Block IIF satellites.…”

“…Two major shortcomings of this approach are that the requirement of two or more receivers makes it difficult to apply to existing monitoring and any updates to existing systems would be costly. Liu and Morton (2019, 2020a, 2020b proposed a machine learning (ML)-based satellite oscillator anomaly detection method using a single receiver. It involves three stages: detection of the phase disturbance using a linear kernel support vector machine (SVM); differentiation of the oscillator anomaly from ionospheric scintillation using the frequency dependence property and a radial basis function (RBF) kernel SVM; and differentiation of the satellite oscillator anomaly from receiver oscillator anomaly by examining the detected phase disturbances on different satellites at the same receiver.…”