Abstract
Radio wave propagation of Global Navigation Satellite System (GNSS) signals via an ionospheric medium offer the opportunity to monitor ionospheric weather nowcasting and forecasting services. The GPS-TEC observations of 20 years are taken into consideration over the Japan region at the GridPoint (134.05° E and 34.95° N). Multivariate Singular Spectrum Analysis (MSSA) is described in this article as a new model for nowcasting and ionospheric prediction. The MSSA algorithm includes a) Time series decomposition, b) reconstruction of approximate components that retain useful components and remove noise components and c) forecast of new data points by a kernel-based extreme learning machine (KELM). An essential modification of MSSA is to maximize the joint variance of all the variables based on Vautard and Ghil (1989) approach. The proposed MSSA achieves high-level now casting illustration at different seasons and solar activities. The first MSSA mode constitutes 99% of the overall variance and characterizes the solar activity variation of the TEC. The RMSE between observed and MSSA model TEC values is 1.52 TECU for the period (1997–2016) and the correlation coefficient is 0.99. Further, MSSA is used as a pre-processing tool for TEC prediction based on KELM. The performance of MSSA-KELM is evaluated in seven cases of different solar periods. The average error measurements during the seven cases are 0.70 (MAE), 5.23 (MAPE), and 0.99 (MSD) respectively. The model achieved higher forecasting accuracy and the lowest training time.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
The modeling part of vTEC was done by considering the corresponding F10.7 and geomagnetic \(\mathit{Ap}\) index data, are downloaded from the NASA-OMNI website (https://omniweb.gsfc.nasa.gov/form/dx1.html). The GPS-TEC dataset at the GridPoint (134.05 E and 34.95 N), generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Broomhead, D.S., King, G.P.: Extracting qualitative dynamics from experimental data. Phys. D, Nonlinear Phenom. 20, 217–236 (1986)
Dabbakuti, J.K., Mallika, Y., Rao, M.V., Rao, K.R., Ratnam, D.V.: Modeling of GPS-TEC using QR-decomposition over the low latitude sector during disturbed geomagnetic conditions. Adv. Space Res. 64, 2088–2103 (2019)
Dabbakuti, J.K., Ratnam, D.V., Sunda, S.: Modelling of ionospheric time delays based on adjusted spherical harmonic analysis. Aviation 20, 1–7 (2016a)
Dabbakuti, J.R.K.K., Devanaboyina, V.R., Kanchumarthi, S.R.: Analysis of local ionospheric variability based on SVD and MDS at low-latitude GNSS stations. Earth Planets Space 68, 94 (2016b)
Dabbakuti, J.R.K.K., G, B.L.: Application of singular spectrum analysis using artificial neural networks in TEC predictions for ionospheric space weather. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12, 5101–5107 (2019)
Dabbakuti, J.R.K.K., Ratnam, D.V.: Performance evaluation of linear time-series ionospheric Total Electron Content model over low latitude Indian GPS stations. Adv. Space Res. 60, 1777–1786 (2017)
Elmunim, N.A., Abdullah, M., Hasbi, A.M., Bahari, S.A.: Comparison of GPS TEC variations with Holt-Winter method and IRI-2012 over Langkawi, Malaysia. Adv. Space Res. 60, 276–285 (2017)
Feliks, Y., Ghil, M., Robertson, A.W.: Oscillatory climate modes in the eastern Mediterranean and their synchronization with the North Atlantic oscillation. J. Climate 23, 4060–4079 (2010)
Huang, G., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw. 17(4), 879–892 (2006)
Mao, T., Wan, W., Yue, X., Sun, L., Zhao, B., Guo, J.: An empirical orthogonal function model of total electron content over China. Radio Sci. 43, 1–12 (2008)
Pyla, R.K., Dabbakuti, J.R.K.K., Mutchakayala, S.G.P., Yashoda, S., Alluri, M.: Modeling of ionospheric characteristics based on canonical correlation analysis at Bangalore for the year 2017. Acta Geod. Geophys. 55, 579–592 (2020)
Ratnam, D.V., Dabbakuti, J.K., Sunda, S.: Modeling of ionospheric time delays based on a multishell spherical harmonics function approach. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 10, 5784–5790 (2017)
Ratnam, D.V., Otsuka, Y., Sivavaraprasad, G., Dabbakuti, J.K.J.A.i.S.R.: Development of multivariate ionospheric TEC forecasting algorithm using linear time series model and ARMA over low-latitude GNSS station. Adv. Space Res. 63(9) 2848–2856 (2019)
Rich, F. J., Sultan, P.J., Burke, W. J.: The 27-day variations of plasma densities and temperatures in the topside ionosphere. J. Geophys. Res. Space Phys. 108, A7 (2003)
Sivapragasam, C., Liong, S.-Y., Pasha, M.F.K.: Rainfall and runoff forecasting with SSA–SVM approach. J. Hydroinform. 3, 141–152 (2001)
Suraj, P.S., Dabbakuti, J.K., Chowdhary, V.R., Tripathi, N.K., Ratnam, D.V.: Linear time series modeling of GPS-derived TEC observations over the Indo-Thailand region. J. Geod. 92(8), 863–872 (2018)
Vautard, R., Ghil, M.: Singular spectrum analysis in nonlinear dynamics, with applications to paleoclimatic time series. Phys. D, Nonlinear Phenom. 35, 395–424 (1989)
Wang, X., Han, M.: Online sequential extreme learning machine with kernels for nonstationary time series prediction. Neurocomputing (Amsterdam) 145, 90–97 (2014)
Wang, X., Wu, J., Liu, C., Wang, S., Niu, W.: A hybrid model based on singular spectrum analysis and support vector machines regression for failure time series prediction. Qual. Reliab. Eng. Int. 32, 2717–2738 (2016)
Wautelet, G., Warnant, R.: Local climatological modeling of ionospheric irregularities detected by GPS in the mid-latitude region. J. Atmos. Sol.-Terr. Phys. 89, 132–143 (2012)
Acknowledgements
The author extended their acknowledge to Institute for Space-Earth Environmental Research, Nagoya University, Nagoya, Japan and Dr. Venkata Ratnam D for providing the data used in this study.
Funding
The author declare that no funds,or grants, or other support were received during the preparation of this manuscript.
Author information
Authors and Affiliations
Contributions
J.R.K. Kumar Dabbakuti is responsible for implementation of the study, analysis of data; Mallika Yarrakula contributed in terms of manuscript preparationl and N. Prabakaran contributed in terms of refinement of model, analysis of the results.
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare no conflicts of interest. The data providing authors had no role in the design of the study; analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yarrakula, M., N, P. & Dabbakuti, J.R.K.K. Modeling and prediction of TEC based on multivariate analysis and kernel-based extreme learning machine. Astrophys Space Sci 367, 34 (2022). https://doi.org/10.1007/s10509-022-04062-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10509-022-04062-5