Journal cover Journal topic
Annales Geophysicae An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 1.621 IF 1.621
  • IF 5-year value: 1.614 IF 5-year 1.614
  • CiteScore value: 1.61 CiteScore 1.61
  • SNIP value: 0.900 SNIP 0.900
  • SJR value: 0.910 SJR 0.910
  • IPP value: 1.58 IPP 1.58
  • h5-index value: 24 h5-index 24
  • Scimago H index value: 80 Scimago H index 80
Discussion papers
https://doi.org/10.5194/angeo-2018-103
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/angeo-2018-103
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Regular paper 25 Sep 2018

Regular paper | 25 Sep 2018

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Annales Geophysicae (ANGEO).

Extending the Coverage Area of Regional Ionosphere Maps Using a Support Vector Machine Algorithm

Mingyu Kim and Jeongrae Kim Mingyu Kim and Jeongrae Kim
  • School of Aerospace and Mechanical Engineering, Korea Aerospace University, Goyang-si, 10540, Korea

Abstract. The coverage of regional ionosphere maps is determined by the distribution of ground 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 ionospheric 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, one 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 – 5°, 10°, and 15° outside the inner data regions. The estimation errors are 0.33 TECU for the 5° region and 1.95 TECU for the 15° 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%.

Mingyu Kim and Jeongrae Kim
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for Authors/Topical Editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Mingyu Kim and Jeongrae Kim
Mingyu Kim and Jeongrae Kim
Viewed  
Total article views: 466 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
417 44 5 466 3 4
  • HTML: 417
  • PDF: 44
  • XML: 5
  • Total: 466
  • BibTeX: 3
  • EndNote: 4
Views and downloads (calculated since 25 Sep 2018)
Cumulative views and downloads (calculated since 25 Sep 2018)
Viewed (geographical distribution)  
Total article views: 460 (including HTML, PDF, and XML) Thereof 459 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 13 Dec 2018
Publications Copernicus
Download
Short summary
Spatial extrapolation of ionosphere TEC map has been carried out using SVM machine learning algorithm. There have been many researches on the temporal extrapolation or prediction of TEC time series, but the spatial extrapolation has been rarely attempted. Some researchers have performed simultaneous extrapolation both in time and in spatial domain, but this researches covers the spatial extrapolation only by using inner TEC map. This spatial TEC extrapolation can be useful for small countries.
Spatial extrapolation of ionosphere TEC map has been carried out using SVM machine learning...
Citation
Share