Extending the coverage area of regional ionosphere maps using a support vector machine algorithm
<p>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 su...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2019-01-01
|
Series: | Annales Geophysicae |
Online Access: | https://www.ann-geophys.net/37/77/2019/angeo-37-77-2019.pdf |
id |
doaj-17a2ef537d364e14a9bdc46f687a9a24 |
---|---|
record_format |
Article |
spelling |
doaj-17a2ef537d364e14a9bdc46f687a9a242020-11-25T00:10:20ZengCopernicus PublicationsAnnales Geophysicae0992-76891432-05762019-01-0137778710.5194/angeo-37-77-2019Extending the coverage area of regional ionosphere maps using a support vector machine algorithmM. Kim0J. Kim1School of Aerospace and Mechanical Engineering, Korea Aerospace University, Goyang-si, 10540, KoreaSchool of Aerospace and Mechanical Engineering, Korea Aerospace University, Goyang-si, 10540, Korea<p>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 <span class="inline-formula">−</span>5, 10, and 15<span class="inline-formula"><sup>∘</sup></span> outside the inner data regions. The extrapolation errors are 0.33 TECU (total electron content unit) for the 5<span class="inline-formula"><sup>∘</sup></span> region and 1.95 TECU for the 15<span class="inline-formula"><sup>∘</sup></span> 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 %.</p>https://www.ann-geophys.net/37/77/2019/angeo-37-77-2019.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
M. Kim J. Kim |
spellingShingle |
M. Kim J. Kim Extending the coverage area of regional ionosphere maps using a support vector machine algorithm Annales Geophysicae |
author_facet |
M. Kim J. Kim |
author_sort |
M. Kim |
title |
Extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
title_short |
Extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
title_full |
Extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
title_fullStr |
Extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
title_full_unstemmed |
Extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
title_sort |
extending the coverage area of regional ionosphere maps using a support vector machine algorithm |
publisher |
Copernicus Publications |
series |
Annales Geophysicae |
issn |
0992-7689 1432-0576 |
publishDate |
2019-01-01 |
description |
<p>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 <span class="inline-formula">−</span>5, 10, and 15<span class="inline-formula"><sup>∘</sup></span>
outside the inner data regions. The extrapolation errors are 0.33 TECU (total electron content unit) for
the 5<span class="inline-formula"><sup>∘</sup></span> region and 1.95 TECU for the 15<span class="inline-formula"><sup>∘</sup></span> 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 %.</p> |
url |
https://www.ann-geophys.net/37/77/2019/angeo-37-77-2019.pdf |
work_keys_str_mv |
AT mkim extendingthecoverageareaofregionalionospheremapsusingasupportvectormachinealgorithm AT jkim extendingthecoverageareaofregionalionospheremapsusingasupportvectormachinealgorithm |
_version_ |
1725408087049764864 |