한국측량학회지 (Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography)

  • 제39권1호
  • /
  • Pages.23-28
  • /
  • 2021
  • /
  • 1598-4850(pISSN)
  • /
  • 2288-260X(eISSN)
한국측량학회 (Korean Society of Surveying, Geodesy, Photogrammetry and Cartography)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 기반 GNSS 천정방향 대류권 습윤지연 추정 연구

Estimation of GNSS Zenith Tropospheric Wet Delay Using Deep Learning

  • Lim, Soo-Hyeon (Dept. of Geoinformation Engineering, Sejong University) ;
  • Bae, Tae-Suk (Dept. of Geoinformation Engineering, Sejong University)
  • 투고 : 2021.01.25
  • 심사 : 2021.02.19
  • 발행 : 2021.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 딥러닝을 활용한 데이터 분석 연구가 다양한 분야에서 진행되고 있다. 본 논문에서는 딥러닝 모델인 MLP (Multi-Layer Perceptron)와 LSTM (Long Short-Term Memory) 모델을 통해 ZWD (Zenith tropospheric Wet Delay)을 추정함으로써 딥러닝을 활용한 GNSS (Global Navigation Satellite System) 기반 기상 연구를 수행하였다. 딥러닝 모델은 기상 데이터와 천정방향 대류권 총 지연, 건조지연을 통해 추정한 ZWD로 학습되었고, 학습에 사용되지 않은 기상 데이터를 학습된 모델에 적용하여 두 모델에서 센티미터 수준의 RMSE (Root Mean Square Error)로 ZWD 결과를 산출하였다. 추후 해안지역의 GNSS 데이터를 함께 사용하고 시간 해상도를 높여 다양한 상황에서도 ZWD가 추정될 수 있도록 추가적인 연구가 수행될 필요가 있다.

Data analysis research using deep learning has recently been studied in various field. In this paper, we conduct a GNSS (Global Navigation Satellite System)-based meteorological study applying deep learning by estimating the ZWD (Zenith tropospheric Wet Delay) through MLP (Multi-Layer Perceptron) and LSTM (Long Short-Term Memory) models. Deep learning models were trained with meteorological data and ZWD which is estimated using zenith tropospheric total delay and dry delay. We apply meteorological data not used for learning to the learned model to estimate ZWD with centimeter-level RMSE (Root Mean Square Error) in both models. It is necessary to analyze the GNSS data from coastal areas together and increase time resolution in order to estimate ZWD in various situations.

키워드

참고문헌

  1. Bae, T.-S. (2018), Accuracy analysis of GNSS-based public surveying and proposal for work processes, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 36, No. 6, pp. 457-467. https://doi.org/10.7848/KSGPC.2018.36.6.457
  2. Bevis, M., Businger, S., Herring, T.A., Rocken, C., Anthes, R., and Ware, R.H. (1992), GPS meteorology-remote sensing of atmospheric water vapor using the Global Positioning System, Journal of Geophysical Research, Vol. 97, No. D14, pp. 15787-15801. https://doi.org/10.1029/92JD01517
  3. GDC (2020), Global Navigation Satellite System Integrated Data Center home page, http://gnssdata.or.kr (last date accessed: 20 November 2020).
  4. Hofmann-Wellenhof, B., Lichtenegger, H., and Collines, J. (2001), GPS Theory and Practice, Springer-Verlag Wien New York, Wien, Austria, 382p.
  5. Jason, H. (2020), Using machine learning to Nowcast precipitation in high resolution, Google AI Blog, https://ai.googleblog.com/2020/01/using-machine-learning-tonowcast.html (last date accessed: 10 November 2020).
  6. Katsougiannopoulos, S. and Pikridas, C. (2009), Prediction of zenith tropospheric delay by multi-layer perceptron, Journal of Applied Geodesy, Vol. 3, No. 4, pp. 223-229. https://doi.org/10.1515/JAG.2009.022
  7. Kim, S.-K. and Bae, T.-S. (2012), Long-term analysis of tropospheric delay and ambiguity resolution rate of GPS data, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 30, No. 6-2, pp. 673-680. https://doi.org/10.7848/ksgpc.2012.30.6-2.673
  8. Kim, J.S. and Bae, T.-S. (2015), Comparative analysis of GNSS precipitable water vapor and meteorological factors, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 33, No. 4, pp. 317-324. https://doi.org/10.7848/ksgpc.2015.33.4.317
  9. Kim, H.-U. and Bae, T.-S. (2017), Preliminary study of deep learning-based precipitation prediction, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 35, No. 5, pp. 423-429. https://doi.org/10.7848/ksgpc.2017.35.5.423
  10. Kim, S.-K. and Bae, T.-S. (2018), Long-term GNSS analysis for local geodetic datum after 2011 Tohoku earthquake, The Journal of Navigation, Vol. 71, No. 1, pp. 117-133. https://doi.org/10.1017/S0373463317000595
  11. KMA (2020), Korea Meteorological Administration home page, http://www.kma.go.kr/home/index.jsp (last date accessed: 10 November 2020).
  12. Nam, J.Y. and Song, D.S. (2019), Retrieval biases analysis on estimation of GNSS precipitable water vapor by tropospheric zenith hydrostatic models, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 37, No. 4, pp. 233-242. https://doi.org/10.7848/KSGPC.2019.37.4.233
  13. Olah, C. (2015), Understanding LSTM Networks, Colah's Blog, http://colah.github.io/posts/2015-08-UnderstandingLSTMs (last date accessed: 23 December 2020).
  14. Saastamoinen, J. (1973), Contribution to theory of atmospheric refraction, Bulletin Geodesique, Vol. 107, pp. 13-34. https://doi.org/10.1007/BF02522083
  15. Selbesoglu, M.O. (2020), Prediction of tropospheric wet delay by an artificial neural network model based on meteorological and GNSS data, Engineering Science and Technology, an International Journal, Vol. 23, No. 5, pp. 967-972. https://doi.org/10.1016/j.jestch.2019.11.006
  16. Seo, Y.-M. (2019), Analysis of Prediction Accuracy of Fine Dust Concentration for Seoul Region Using LSTM Model, Master's thesis, Sejong University, Seoul, Korea, 77p.