Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm
This paper presents a random forest-based machine learning algorithm to automatically detect satellite oscillator anomalies using dual- or triple-frequency GPS carrier phase measurements. The algorithm can distinguish satellite oscillator anomalies from other GPS carrier phase disturbances including...
Published in: | NAVIGATION: Journal of the Institute of Navigation |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Institute of Navigation
2022
|
Subjects: | |
Online Access: | https://doi.org/10.33012/navi.500 https://doaj.org/article/45baf202bd524632a69d171afba44247 |
id |
ftdoajarticles:oai:doaj.org/article:45baf202bd524632a69d171afba44247 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:45baf202bd524632a69d171afba44247 2024-01-14T10:07:19+01:00 Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm Yunxiang Liu Y. Jade Morton 2022-01-01T00:00:00Z https://doi.org/10.33012/navi.500 https://doaj.org/article/45baf202bd524632a69d171afba44247 EN eng Institute of Navigation https://navi.ion.org/content/69/1/navi.500 https://doaj.org/toc/2161-4296 2161-4296 doi:10.33012/navi.500 https://doaj.org/article/45baf202bd524632a69d171afba44247 Navigation, Vol 69, Iss 1 (2022) Canals and inland navigation. Waterways TC601-791 Naval Science V article 2022 ftdoajarticles https://doi.org/10.33012/navi.500 2023-12-17T01:42:45Z This paper presents a random forest-based machine learning algorithm to automatically detect satellite oscillator anomalies using dual- or triple-frequency GPS carrier phase measurements. The algorithm can distinguish satellite oscillator anomalies from other GPS carrier phase disturbances including ionospheric scintillation and receiver oscillator anomalies. Carrier phase power spectral density and carrier phase ratios between carriers are extracted from measurements and applied as input features to the random-forest algorithm. The method is trained using data collected at seven GNSS monitoring stations located in Alaska, Ascension Island, Greenland, Hong Kong, Peru, Puerto Rico, and Singapore. The overall detection accuracies of 98.4% and 99.0% are achieved for dual- and triple-frequency signals, respectively. The method outperforms other machine learning algorithms. The preliminary detection results demonstrate that the method presented can be employed on a global satellite oscillator anomaly monitoring system. Article in Journal/Newspaper Greenland Alaska Directory of Open Access Journals: DOAJ Articles Greenland NAVIGATION: Journal of the Institute of Navigation 69 1 navi.500 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Canals and inland navigation. Waterways TC601-791 Naval Science V |
spellingShingle |
Canals and inland navigation. Waterways TC601-791 Naval Science V Yunxiang Liu Y. Jade Morton Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
topic_facet |
Canals and inland navigation. Waterways TC601-791 Naval Science V |
description |
This paper presents a random forest-based machine learning algorithm to automatically detect satellite oscillator anomalies using dual- or triple-frequency GPS carrier phase measurements. The algorithm can distinguish satellite oscillator anomalies from other GPS carrier phase disturbances including ionospheric scintillation and receiver oscillator anomalies. Carrier phase power spectral density and carrier phase ratios between carriers are extracted from measurements and applied as input features to the random-forest algorithm. The method is trained using data collected at seven GNSS monitoring stations located in Alaska, Ascension Island, Greenland, Hong Kong, Peru, Puerto Rico, and Singapore. The overall detection accuracies of 98.4% and 99.0% are achieved for dual- and triple-frequency signals, respectively. The method outperforms other machine learning algorithms. The preliminary detection results demonstrate that the method presented can be employed on a global satellite oscillator anomaly monitoring system. |
format |
Article in Journal/Newspaper |
author |
Yunxiang Liu Y. Jade Morton |
author_facet |
Yunxiang Liu Y. Jade Morton |
author_sort |
Yunxiang Liu |
title |
Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
title_short |
Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
title_full |
Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
title_fullStr |
Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
title_full_unstemmed |
Improved Automatic Detection of GPS Satellite Oscillator Anomaly using a Machine-Learning Algorithm |
title_sort |
improved automatic detection of gps satellite oscillator anomaly using a machine-learning algorithm |
publisher |
Institute of Navigation |
publishDate |
2022 |
url |
https://doi.org/10.33012/navi.500 https://doaj.org/article/45baf202bd524632a69d171afba44247 |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
Greenland Alaska |
genre_facet |
Greenland Alaska |
op_source |
Navigation, Vol 69, Iss 1 (2022) |
op_relation |
https://navi.ion.org/content/69/1/navi.500 https://doaj.org/toc/2161-4296 2161-4296 doi:10.33012/navi.500 https://doaj.org/article/45baf202bd524632a69d171afba44247 |
op_doi |
https://doi.org/10.33012/navi.500 |
container_title |
NAVIGATION: Journal of the Institute of Navigation |
container_volume |
69 |
container_issue |
1 |
container_start_page |
navi.500 |
_version_ |
1788061738196795392 |