Skip to main content
SpringerLink
Log in

Influence of Advance Time on Accuracy of the Ionospheric Total Electron Content Forecast

  • Conference paper
  • First Online:
Telecommunications and Remote Sensing (ICTRS 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1990))

Included in the following conference series:

  • 52 Accesses

Abstract

The total electron content of the ionosphere plays an important role in determining the operational conditions for various technological systems, therefore, great importance is attached to its study and forecasting. In connection with the revival of the intensive use of machine learning methods, in the first work of the authors, using the example of the reference station Juliusruh and 2015, the effectiveness of traditional models of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) was studied. In this paper, in order to increase the accuracy of the forecast, several modifications of these methods were proposed: 1) implementing the proposed MidR and InR architectures based on LSTM and GRU, 2) modifying the architectures using bidirectional algorithms, 3) using the temporal convolution architecture separately and jointly with bidirectional networks, thus, defining 10 architectures under study. In addition to the previous results for an advance time of 2h, the forecast was made for the traditionally used period of 24h. It is shown that four architectures of the first group and separately TCN provide prediction accuracy at the level of literature data, and for prediction for 24h, the prediction accuracy is 2 times worse than for 2h. The inclusion of the bidirectional algorithm leads to a significant increase in the accuracy of the forecast, with the mostly comparable results for various advance times, with quantitative estimates of 0.4–0.5 TECU for MAE, 0.6–1.0 TECU for RMSE, 5–7% for MAPE. The same estimates were obtained for three stations along the 30° E meridian.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Schrijver, C.J., Kauristie, K., Aylward, A.D., et al.: Understanding space weather to shield society: a global road map for 2015–2025 commissioned by COSPAR and ILWS. Adv. Space Res. 55(12), 2745–2807 (2015). https://doi.org/10.1016/j.asr.2015.03.023

    Article  Google Scholar 

  2. McGranaghan, R.M., Camporeale, E., Georgoulis, M., Anastasiadis, A.: Space weather research in the digital age and across the full data lifecycle: introduction to the topical issue. J. Space Weather Space Clim. 11, 50 (2021). https://doi.org/10.1051/swsc/2021037

    Article  Google Scholar 

  3. Yu, S., Ma, J.: Deep learning for geophysics: current and future trends. Rev. Geophys. 59, e2021RG000742 (2021). https://doi.org/10.1029/2021RG000742

  4. Kalinin, Y., Repin, A., Khotenko, E.N.: Applied geophysics of the ionosphere and the actual application of artificial intelligence technology. Geliogeophys. Res. 30, 21–29 (2021). https://doi.org/10.54252/2304-7380_2021_30_21

    Article  Google Scholar 

  5. Wang, J., Yu, Q., Shi, Y., Liu, Y., Yang, C.: An explainable dynamic prediction method for ionospheric foF2 based on machine learning. Remote Sens. 15, 1256 (2023). https://doi.org/10.3390/rs15051256

    Article  Google Scholar 

  6. Xie, T., Dai, Z., Zhu, X., Chen, B., Ran, C.: LSTM-based short-term ionospheric TEC forecast model and positioning accuracy analysis. GPS Solutions 27, 66 (2023). https://doi.org/10.1007/s10291-023-01406-8

    Article  Google Scholar 

  7. Nishioka, M., Saito, S., Tao, C., Shiota, D., Tsugawa, T., Ishii, M.: Statistical analysis of ionospheric total electron content (TEC): long-term estimation of extreme TEC in Japan Earth. Planets Space 73(52), 1–12 (2021). https://doi.org/10.1186/s40623-021-01374-8

    Article  Google Scholar 

  8. Hernández-Pajares, M., et al.: The IGS VTEC maps: a reliable source of ionospheric information since 1998. J. Geod. 83, 263–275 (2009)

    Article  Google Scholar 

  9. Badeke, R., Borries, C., Hoque, M.M., Minkwitz, D.: Empirical forecast of quiet time ionospheric total electron content maps over Europe. Adv. Space Res. 61, 2881–2890 (2018). https://doi.org/10.1016/j.asr.2018.04.010

    Article  Google Scholar 

  10. Garcia-Rigo, A., et al.: Global prediction of the vertical total electron content of the ionosphere based on GPS data. Radio Sci. 46, RS0D25 (2011). https://doi.org/10.1029/2010RS004643

  11. Jakowski, N., Hoque, M.M., Mayer, C.: A new global TEC model for estimating transionospheric radio wave propagation errors. J. Geod. 85, 965–974 (2011). https://doi.org/10.1007/s00190-011-0455-1

    Article  Google Scholar 

  12. Kaselimi, M., Voulodimos, A., Doulamis, N., Doulamis, A., Delikaraoglou, D.: Deep recurrent neural networks for ionospheric variations estimation using GNSS measurements. IEEE Trans. Geosci. Remote Sens. 60, 1–15 (2022). https://doi.org/10.1109/TGRS.2021.3090856

    Article  Google Scholar 

  13. Lin, X., et al.: A spatiotemporal network model for global ionospheric TEC forecasting. Remote Sens. 14, 1717 (2022). https://doi.org/10.3390/rs14071717

    Article  Google Scholar 

  14. Sun, W., et al.: Forecasting of ionospheric vertical total electron content (TEC) using LSTM networks. In: Proceedings of the 2017 International Conference on Machine Learning and Cybernetics, Ningbo, China, 9–12 July 2017

    Google Scholar 

  15. Sun, W., Xu, L., Huang, X., Zhang, W., Yuan, T., Yan, Y.: Bidirectional LSTM for ionospheric vertical total electron content (TEC) forecasting. In: Proceedings of IEEE Vision and Communication Image Processing (VCIP), December 2017, pp. 1–4 (2017). https://doi.org/10.1109/VCIP.2017.8305097

  16. Sivakrishna, K., Ratnam, D.V., Sivavaraprasad, G.: A bidirectional deep-learning algorithm to forecast regional ionospheric TEC maps. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 15, 4531–4543 (2022). https://doi.org/10.1109/JSTARS.2022.3180940

    Article  Google Scholar 

  17. Tang, J., Li, Y., Ding, M., Liu, H., Yang, D., Wu, X.: An ionospheric TEC forecasting model based on a CNN-LSTM-attention mechanism neural network. Remote Sens. 14, 2433 (2022). https://doi.org/10.3390/rs14102433

    Article  Google Scholar 

  18. Weng, J., Liu, Y., Wang, J.: A model-assisted combined machine learning method for ionospheric TEC prediction. Remote Sens. 15, 2953 (2023). https://doi.org/10.3390/rs15122953

    Article  Google Scholar 

  19. Iluore, K., Lu, J.: Long short-term memory and gated recurrent neural networks to predict the ionospheric vertical total electron content. Adv. Space Res. 70, 652–665 (2022). https://doi.org/10.1016/j.asr.2022.04.066

    Article  Google Scholar 

  20. Natras, R., Soja, B., Schmidt, M.: Ensemble machine learning of random forest, AdaBoost and XGBoost for vertical total electron content forecasting. Remote Sens. 14(3547), 1–34 (2022). https://doi.org/10.3390/rs14153547

    Article  Google Scholar 

  21. Morozova, A.L., Barata, T., Barlyaeva, T.: PCA-MRM model to forecast TEC at middle latitudes. Atmosphere 13, 323 (2022). https://doi.org/10.3390/atmos13020323

    Article  Google Scholar 

  22. Kharakhashyan, A., Maltseva, O., Glebova, G.: Forecasting the total electron content TEC of the ionosphere using space weather parameters. In: Proceedings of the 2021 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE), Cleveland, OH, USA, 12–14 October 2021, pp. 31–36 (2021). https://doi.org/10.1109/WiSEE50203.2021.9613829

  23. Chen, J., Zhi, N., Liao, H., Lu, M., Feng, S.: Global forecasting of ionospheric vertical total electron contents via ConvLSTM with spectrum analysis. GPS Solutions 26, 69 (2022). https://doi.org/10.1007/s10291-022-01253-z

    Article  Google Scholar 

  24. Chen, Z., Liao, W., Li, H., Wang, J., Deng, X., Hong, S.: Prediction of global ionospheric TEC based on deep learning. Space Weather 20, e2021SW002854 (2022). https://doi.org/10.1029/2021SW002854

  25. Danilov, A.D., Konstantinova, A.V.: Detailed analysis of the behavior of the F2-layer critical frequency prior to magnetic storms. 10. Proportion between negative and positive events. Geliogeophys. Res. 35, 3–11 (2022). https://doi.org/10.5425/2304-7380_2022_35_3

  26. Danilov, A.D., Konstantinova, A.V.: Ionospheric precursors of magnetic storms. 3. Analysis of juliusruh station data. Geomagn. Aeron. (Engl. Transl.) 61(3), 341–348 (2021). https://doi.org/10.1134/S0016793221030087

  27. Ren, X., Yang, P., Liu, H., Chen, J., Liu, W.: Deep learning for global ionospheric TEC forecasting: different approaches and validation. Space Weather 20, e2021SW003011 (2022). https://doi.org/10.1029/2021SW003011

  28. Hochreiter, S., Schmidhuber, J.: Long short-term memory neural computation. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  29. Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078v3 [cs.CL] 3, (2014). https://arxiv.org/pdf/1406.1078.pdf

  30. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy: AISTATS, pp. 249–356 (2010)

    Google Scholar 

  31. Saxe, A.M., McClelland, J.L., Ganguli, S.: Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv preprint arXiv:1312.6120 (2013)

  32. Bai, S., Kolter, J.Z., Koltun, J.V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modelling, 19 April, pp. 1–14 (2018, preprint, submitted). https://arxiv.org/abs/1803.01271

Download references

Acknowledgments

The authors are grateful to the developers of websites: http://omniweb.gsfc.nasa.gov/form/dx1.html, ftp://cddis.gsfc.nasa.gov/pub/gps/products/ionex/. The research was financially supported by Ministry of Science and Higher Education of the Russian Federation (State task in the field of scientific activity 2023).

Author information

Authors and Affiliations

  1. Institute for Physics, Southern Federal University, Rostov-on-Don, 344090, Russia

    Olga A. Maltseva & Artem M. Kharakhashyan

Authors
  1. Olga A. Maltseva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Artem M. Kharakhashyan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Olga A. Maltseva .

Editor information

Editors and Affiliations

  1. Institute of Mathematics and Informatics, Bulgarian Academy of Sciences, Sofia, Bulgaria

    Boris Shishkov

  2. Nikola Vaptsarov Naval Academy, Varna, Bulgaria

    Andon Lazarov

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Maltseva, O.A., Kharakhashyan, A.M. (2023). Influence of Advance Time on Accuracy of the Ionospheric Total Electron Content Forecast. In: Shishkov, B., Lazarov, A. (eds) Telecommunications and Remote Sensing. ICTRS 2023. Communications in Computer and Information Science, vol 1990. Springer, Cham. https://doi.org/10.1007/978-3-031-49263-1_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-49263-1_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-49262-4

  • Online ISBN: 978-3-031-49263-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation