Time Series Forecasting Model of the Ionospheric f_o F2 Using Facebook Prophet
DOI:
https://doi.org/10.63746/njtd.v23i1.4395Keywords:
Ionosphere, Critical frequency, Facebook Prophet, f_o F2, Time series forecastingAbstract
The study of ionospheric behaviour is critical for maintaining the reliability of space-based technologies, including HF communication links and Global Navigation Satellite Systems (GNSS). Ionospheric delays can significantly degrade the performance and accuracy of trans-ionospheric signals; thus, robust forecasting of the parameter is essential. This study uses a long-term dataset (2009 to 2016 for training) of observations from the Jicamarca Observatory in Peru to implement and evaluate the Facebook Prophet (FB-Prophet) time-series forecasting technique. For the years 2017 to 2019, the FB-Prophet model was used to forecast. Its performance was verified using independent observational test data and accepted empirical standards, namely the IRI-2020 URSI and CCIR sub-options. The study results indicate that FB-Prophet effectively reproduces the diurnal and semi-annual variations in the ionosphere. During the initial forecast period (2017 to 2018), FB-Prophet demonstrated superior alignment with observational fluctuations compared to empirical models, achieving a Root Mean Square Error (RMSE) of 0.71 MHz and a Mean Absolute Error (MAE) of 0.57 MHz. However, as the forecast horizon extended into the deep solar minimum of 2019, the CCIR model exhibited higher precision with a minimum RMSE of 0.15 MHz, while FB-Prophet's uncertainty interval expanded as the lead time increased and the solar environment transitioned into a significantly quieter regime. These findings demonstrate that FB-Prophet’s time-series decomposition is a highly effective tool for multi-year ionospheric forecasting at equatorial latitudes. The study highlights that while empirical models remain reliable for long-term climatological averages, the FB-Prophet approach offers enhanced predictive accuracy for capturing non-linear variations during periods of moderate solar activity (107.68 ± 33.81 sfu).
References
Acharya, R., Roy, B., Sivaraman, M., & Dasgupta, A. (2012). Improved predictions of equatorial TEC for real time applications. Advances in Space Research, 49(4), 694-699. https://doi.org/10.1016/j.asr.2011.11.006
Adebesin, B., Adekoya, B., Ikubanni, S., Adebiyi, S., Adebesin, O., Joshua, B., & Olonade, K. (2014). Ionospheric foF2 morphology and response of F2 layer height over Jicamarca during different solar epochs and comparison with IRI-2012 model. Journal of Earth System Science, 123(4), 751-765. https://doi.org/10.1007/s12040-014-0435-y
Akala, A., Adeloye, A., & Somoye, E. (2010). Ionospheric foF2 variability over the Southeast Asian sector. Journal of Geophysical Research: Space Physics, 115(A9). https://doi.org/10.1029/2010JA015250
Athieno, R., Jayachandran, P., & Themens, D. (2017). A neural network-based foF2 model for a single station in the polar cap. Radio Science, 52(6), 784–796. https://doi.org/10.1002/2016RS006192
Bai, H., Feng, F., Wang, J., & Wu, T. (2020). A combination prediction model of long-term ionospheric foF2 based on entropy weight method. Entropy, 22(4), 442. https://doi.org/10.3390/e22040442
Basu, S., Groves, K., Basu, S., & Sultan, P. (2002). Specification and forecasting of scintillations in communication/navigation links: Current status and future plans. Journal of Atmospheric and Solar-Terrestrial Physics, 64(16), 1745–1754. https://doi.org/10.1016/S1364-6826(02)00124-4
Bello, S. A., Abdullah, M., Hamid, N. A., Reinisch, B., Yoshikawa, A., & Fujimoto, A. (2019). Response of ionospheric profile parameters to equatorial electrojet over Peruvian station. Earth and Space Science, 6(4), 617–628. https://doi.org/10.1029/2018EA000537
Bello, S. A., Abdullah, M., & Hamid, N. S. A. (2017a). Investigation of ionospheric minimum frequency near dip equator. Advanced Science Letters, 23(2), 1329–1332. https://doi.org/10.1166/asl.2017.8357
Bello, S. A., Abdullah, M., Hamid, N. S. A., & Reinisch, B. W. (2017b). Comparison of ionospheric profile parameters with IRI-2012 model over Jicamarca. Journal of Physics: Conference Series, 852(012016). https://doi.org/10.1088/1742-6596/852/1/012016
Bello, S. A., Abdullah, M., Hamid, N. S. A., Yoshikawa, A., & Olawepo, A. (2017c). Variations of B0 and B1 with the solar quiet Sq-current system and comparison with IRI-2012 model at Ilorin. Advances in Space Research, 60(2), 307–316. https://doi.org/10.1016/j.asr.2017.02.003
Bello, S. A., Abdullah, M., Hamid, N., Yusuf, K. A., Yoshikawa, A., & Fujimoto, A. (2023). Robust least square modelling for selected daytime ionospheric parameters using geomagnetic observations at low latitudes. Advances in Space Research, 72(5), 1615-1633. https://doi.org/10.1016/j.asr.2023.04.040.
Bello, S., Yusuf, K., Sharafa, S., Shehu, S., Joseph, O., & Oluwafemi, L. (2025). DINData: A Windows Software to Reformat and Clean Digisonde Numeric Dataset. BIMA Journal of Science and Technology Gombe, 9(4A), 114–127. https://doi.org/10.64290/bima.v9i4A.1404
Bi, C., Ren, P., Yin, T., Xiang, Z., & Zhang, Y. (2022). Modeling and forecasting ionospheric foF2 variation in the low latitude region during low and high solar activity years. Remote Sensing, 14(21), 5418. https://doi.org/10.3390/rs14215418
Bilitza, D., Altadill, D., Truhlik, V., Shubin, V., Galkin, I., Reinisch, B., & Huang, X. (2017). International Reference Ionosphere 2016: From ionospheric climate to real?time weather predictions. Space Weather, 15(2), 418–429. https://doi.org/10.1002/2016SW001593
Bilitza, D., Pezzopane, M., Truhlik, V., Altadill, D., Reinisch, B. W., & Pignalberi, A. (2022). The international reference ionosphere model: A review and description of an ionospheric benchmark. Reviews of Geophysics, 60(4), e2022RG000792. https://doi.org/10.1029/2022RG000792
Elseidi, M. (2024). A hybrid Facebook Prophet-ARIMA framework for forecasting high-frequency temperature data. Modeling Earth Systems and Environment, 10(2), 1855–1867. https://doi.org/10.1007/s40808-023-01874-4
Galkin, I., Reinisch, B. W., Huang, X., & Khmyrov, G. M. (2013). Confidence score of ARTIST-5 ionogram autoscaling. Ionosonde Network Advisory Group (INAG) Bulletin No, 73, 1–7. https://www.ursi.org/files/CommissionWebsites/INAG/web-69/2008/artist5-inag.pdf
Harvey, A. C., & Peters, S. (1990). Estimation procedures for structural time series models. Journal of Forecasting, 9(2), 89–108. https://doi.org/10.1002/for.3980090203
Huang, L., Wu, H., Lou, Y., Zhang, H., Liu, L., & Huang, L. (2022). Spatiotemporal analysis of regional ionospheric TEC prediction using multi-factor NeuralProphet model under disturbed conditions. Remote Sensing, 15(1), 195. https://doi.org/10.3390/rs15010195
Kelley, M. C. (2009). The Earth’s ionosphere. Academic Press (2nd ed., Vol. 96). International Geophysics Book Series.
Kouris, S., & Nissopoulos, J. (1994). Variation of foF2 with solar activity. Advances in Space Research, 14(12), 51–54. https://doi.org/10.1016/0273-1177(94)90238-0
Liu, J. Y., Chen, Y. I., & Lin, J. S. (2003). Statistical investigation of the saturation effect in the ionospheric foF2 versus sunspot, solar radio noise, and solar EUV radiation. Journal of Geophysical Research: Space Physics, 108. https://doi.org/10.1029/2001ja007543
Oo, Z. Z., & Phyu, S. (2020). Time series prediction based on Facebook prophet: A case study, temperature forecasting in myintkyina. International Journal of Applied Mathematics Electronics and Computers, 8(4), 263–267. https://doi.org/10.18100/ijamec.816894
Reinisch, B., Huang, X., Galkin, I., Paznukhov, V., & Kozlov, A. (2005). Recent advances in real-time analysis of ionograms and ionospheric drift measurements with digisondes. Journal of Atmospheric and Solar-Terrestrial Physics, 67(12), 1054–1062. https://doi.org/10.1016/j.jastp.2005.01.009
Reinisch, B. W., & Galkin, I. A. (2011). Global ionospheric radio observatory (GIRO). Earth, Planets and Space, 63(4), 377–381. https://doi.org/10.5047/eps.2011.03.001
Tang, J., Li, Y., Yang, D., & Ding, M. (2022). An approach for predicting global ionospheric TEC using machine learning. Remote Sensing, 14(7), 1585. https://doi.org/10.3390/rs14071585
Tapping, K. F. (2013). The 10.7 cm solar radio flux (F10. 7). Space Weather, 11(7), 394–406. https://doi.org/10.1002/swe.20064
Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37–45. https://doi.org/10.1080/00031305.2017.1380080
Toharudin, T., Pontoh, R. S., Caraka, R. E., Zahroh, S., Lee, Y., & Chen, R. C. (2023). Employing long short-term memory and Facebook prophet model in air temperature forecasting. Communications in Statistics-Simulation and Computation, 52(2), 279–290. https://doi.org/10.1080/03610918.2020.1854302
Tsagouri, I., Koutroumbas, K., & Belehaki, A. (2009). Ionospheric foF2 forecast over Europe based on an autoregressive modeling technique driven by solar wind parameters. Radio Science, 44(01), 1–21. https://doi.org/10.1029/2008RS004112
Vishwas, B., & Patel, A. (2020). Hands-on time series analysis with Python. Springer. https://doi.org/10.1007/978-1-4842-5992-4
Wang, G. J., Shi, J. K., Wang, Z., Wang, X., Romanova, E., Ratovsky, K., & Polekh, N. M. (2017). Solar cycle variation of ionospheric parameters over the low latitude station Hainan, China, during 2002–2012 and its comparison with IRI-2012 model. Advances in Space Research, 60(2), 381–395. https://doi.org/10.1016/j.asr.2016.12.013
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nigerian Journal of Technological Development
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
In accordance with the Copyright Act of 1976, which became effective January 1, 1978, the following statement signed by each author must accompany the manuscript submitted: "I, the undersigned author, transfer all copyright ownership of the manuscript referenced above to the Nigerian Journal of Technological Development, in the event the work is published. I warrant that the article is original, does not infringe upon any copyright or other proprietary right of any third party, is not under consideration by another journal, and has not been published previously. I have reviewed and approved the submitted version of the manuscript and agree to its publication in the Nigerian Journal of Technological Development." A copyright transfer form can be downloaded from the NJTD Website (http://njtd.com.ng/index.php/njtd). Author(s) will be consulted, whenever possible, regarding republication of material. All authors must have access to the data presented, and the authors and sponsor (if applicable) must agree to share original data with the editor if requested.
