Ionospheric TEC modeling using COSMIC-2 GNSS radio occultation and artificial neural networks over Egypt
-
Ahmed Sherif
,
Mostafa Rabah
Abstract
The ionospheric delay significantly impacts GNSS positioning accuracy. To address this, an Artificial Neural Network (ANN) was developed using the high-quality COSMIC-2 ionospheric profile dataset to predict the Total Electron Content (TEC). ANNs are adept at addressing both linear and nonlinear challenges. For this research, eight distinct ANNs were cultivated. These ANNs were designed with the following inputs Year, Month, Day, Hour, Latitude, and Longitude. Along with solar and geomagnetic parameters such as the F10.7 solar radio flux index, the Sunspot Number (SSN), the Kp index, and the ap index. The goal was to discern the most influential parameters on ionosphere prediction. After pinpointing these key parameters, an enhanced model utilizing a pioneering technique of a secondary ANN was employed with the main ANN to predict TEC values for events in 2023. The study’s findings indicate that solar parameters markedly enhance the model’s accuracy. Notably, the augmented model featuring a prelude secondary network achieved a stellar correlation coefficient of 0.99. Distributionally, 41 % of predictions aligned within the (−1≤ ΔTEC ≤1) TECU spectrum, 28 % nestled within the (1< ΔTEC ≤2) and (−2≤ ΔTEC <−1) TECU ambit, while a substantial 30 % spanned the broader (2< ΔTEC ≤5) and (−5≤ ΔTEC <−2) TECU range. In essence, this research underscores the potential of incorporating solar parameters and advanced neural network techniques to refine ionospheric delay predictions, thus boosting GNSS positioning precision.
Acknowledgment
The authors would like to acknowledge the Taiwan Analysis Center for COSMIC (TACC) for providing the FORMOSAST-7/COSMIC-2 (F7/C2) data used in the study. Furthermore, they extend their appreciation to the COSMIC Data Analysis and Archive Center (CDAAC) for the IonPrf dataset utilized in this research, which was accessed from the CDAAC website (http://COSMIC-io.COSMIC.ucar.edu/cdaac/index.html).
References
1. Basciftci, F, Inal, C, Yildirim, O, Bulbul, S. Determining regional ionospheric model and comparing with global models. Geod Vestn 2017;61:427–40. https://doi.org/10.15292//geodetski-vestnik.2017.03.427-440.Search in Google Scholar
2. Mack, MJr. A statistical comparison of vertical total electron content (TEC) from three ionospheric models; 2008. Available from: http://www.swpc.noaa.gov/info/Iono.pdf.Search in Google Scholar
3. Hofmann-Wellenhof, B, Lichtenegger, H, Wasle, E. GNSS global navigation satellite systems. Vienna: Springer Science & Business Media; 2008.Search in Google Scholar
4. Ludwig-Barbosa, V, Sievert, T, Rasch, J, Carlström, A, Pettersson, MI, Vu, VT. Evaluation of ionospheric scintillation in GNSS radio occultation measurements and simulations. Radio Sci 2020;55:1–13. https://doi.org/10.1029/2019rs006996.Search in Google Scholar
5. Sherif, A, Rabah, M, Mousa, AE, Zaki, A, Sedeek, A. Assessing the performance of IRI-2016 and IRI-2020 models using COSMIC-2 GNSS radio occultation TEC data under different magnetic activities over Egypt. J Appl Geodesy 2023:1–14. https://doi.org/10.1515/jag-2023-0068.Search in Google Scholar
6. Ren, X, Li, Y, Mei, D, Zhu, W, Zhang, X. Improving topside ionospheric empirical model using FORMOSAT-7/COSMIC-2 data. J Geodesy 2023;97:1–12. https://doi.org/10.1007/s00190-023-01710-8.Search in Google Scholar
7. Tebabal, A, Radicella, SM, Damtie, B, Migoya-Orue, Y, Nigussie, M, Nava, B. Feed forward neural network based ionospheric model for the East African region. J Atmos Sol Terr Phys 2019;191:105052. https://doi.org/10.1016/j.jastp.2019.05.016.Search in Google Scholar
8. Watthanasangmechai, K, Supnithi, P, Lerkvaranyu, S, Tsugawa, T, Nagatsuma, T, Maruyama, T. TEC prediction with neural network for equatorial latitude station in Thailand. Earth Planets Space 2012;64:473–83. https://doi.org/10.5047/eps.2011.05.025.Search in Google Scholar
9. Athieno, R, Jayachandran, PT, Themens, DR. A neural network-based foF2 model for a single station in the polar cap. Radio Sci 2017;52:784–96. https://doi.org/10.1002/2016rs006192.Search in Google Scholar
10. Shi, S, Wu, S, Zhang, K, Li, W, Shi, J, Song, F. An investigation of a new artificial neural network-based TEC model using ground-based GPS and COSMIC-2 measurements over low latitudes. Adv Space Res 2022;70:2522–40. https://doi.org/10.1016/j.asr.2022.07.027.Search in Google Scholar
11. Li, W, Huang, L, Zhang, S, Chai, Y. Assessing global ionosphere TEC maps with satellite altimetry and ionospheric radio occultation observations. Sensors 2019;19:5489. https://doi.org/10.3390/s19245489.Search in Google Scholar PubMed PubMed Central
12. Sanchez, L. Global geodetic observing system (GGOS). https://ggos.org/item/gnss-radio-occultation/#learn-this [Accessed 1 Aug 2023].Search in Google Scholar
13. Fu, N, Guo, P, Wu, M, Huang, Y, Hu, X, Hong, Z. The two-parts step-by-step ionospheric assimilation based on ground-based/spaceborne observations and its verification. Rem Sens 2019;11:1–26. https://doi.org/10.3390/rs11101172.Search in Google Scholar
14. Alizadeh, MM, Schuh, H, Todorova, S, Schmidt, M. Global ionosphere maps of VTEC from GNSS, satellite altimetry, and formosat-3/COSMIC data. J Geodesy 2011;85:975–87. https://doi.org/10.1007/s00190-011-0449-z.Search in Google Scholar
15. Bishop, CM. Pattern recognition and machine learning. New York: Springer; 2006, vol 4.Search in Google Scholar
16. Haykin, S. Neural networks and learning machines, 3rd ed. Upper Saddle River, New Jersey: Pearson Prentice Hall; 2009:934 p.Search in Google Scholar
17. Goodfellow, I, Bengio, Y, Courville, A. Deep learning. Cambridge: MIT Press; 2016.Search in Google Scholar
18. Rumelhart, DE, Hinton, GE, Williams, RJ. Learning representations by back-propagating errors. Nature 1986;323:533–6. https://doi.org/10.1038/323533a0.Search in Google Scholar
19. Okoh, D, Seemala, G, Rabiu, B, Habarulema, JB, Jin, S, Shiokawa, K, et al.. A neural network-based ionospheric model over Africa from constellation observing system for meteorology, ionosphere, and climate and ground global positioning system observations. J Geophys Res Space Phys 2019;124:10512–32. https://doi.org/10.1029/2019ja027065.Search in Google Scholar
20. Ruder, S. An overview of gradient descent optimization algorithms; 2016. Available from: http://arxiv.org/abs/1609.04747.Search in Google Scholar
21. Altinay, O, Tulunay, E, Tulunay, Y. Forecasting of ionospheric critical frequency using neural networks. Geophys Res Lett 1997;24:1467–70. https://doi.org/10.1029/97gl01381.Search in Google Scholar
22. Wackerly, D, Mendenhall, W, Scheaffer, RL. Mathematical statistics with applications, 7th ed. Boston: Thomson Brooks/Cole; 2008:944 p.Search in Google Scholar
23. Hyndman, RJ, Athanasopoulos, G. Forecasting: principles and practice [Internet]. OTexts; 2018:384 p. Available from: https://otexts.org/fpp2/.Search in Google Scholar
24. Willmott, CJ, Matsuura, K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 2005;30:79–82. https://doi.org/10.3354/cr030079.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Original Research Articles
- Ionospheric TEC modeling using COSMIC-2 GNSS radio occultation and artificial neural networks over Egypt
- Regional GPS orbit determination using code-based pseudorange measurement with residual correction model
- Analysis of different combinations of gravity data types in gravimetric geoid determination over Bali
- Assessment of satellite images terrestrial surface temperature and WVP using GNSS radio occultation data
- GNSS positioning accuracy performance assessments on 1st and 2nd generation SBAS signals in Thailand
- Differential synthetic aperture radar (SAR) interferometry for detection land subsidence in Derna City, Libya
- Advanced topographic-geodetic surveys and GNSS methodologies in urban planning
- Detection of GNSS ionospheric scintillations in multiple directions over a low latitude station
- Spatiotemporal postseismic due to the 2018 Lombok earthquake based on insar revealed multi mechanisms with long duration afterslip
- Practical implications in the interpolation methods for constructing the regional mean sea surface model in the eastern Mediterranean Sea
- Validation of a tailored gravity field model for precise quasigeoid modelling over selected sites in Cameroon and South Africa
- Evaluation of ML-based classification algorithms for GNSS signals in ocean environment
- Development of a hybrid geoid model using a global gravity field model over Sri Lanka
- Implementation of GAGAN augmentation on smart mobile devices and development of a cooperative positioning architecture
- On the GPS signal multipath at ASG-EUPOS stations
Articles in the same Issue
- Frontmatter
- Original Research Articles
- Ionospheric TEC modeling using COSMIC-2 GNSS radio occultation and artificial neural networks over Egypt
- Regional GPS orbit determination using code-based pseudorange measurement with residual correction model
- Analysis of different combinations of gravity data types in gravimetric geoid determination over Bali
- Assessment of satellite images terrestrial surface temperature and WVP using GNSS radio occultation data
- GNSS positioning accuracy performance assessments on 1st and 2nd generation SBAS signals in Thailand
- Differential synthetic aperture radar (SAR) interferometry for detection land subsidence in Derna City, Libya
- Advanced topographic-geodetic surveys and GNSS methodologies in urban planning
- Detection of GNSS ionospheric scintillations in multiple directions over a low latitude station
- Spatiotemporal postseismic due to the 2018 Lombok earthquake based on insar revealed multi mechanisms with long duration afterslip
- Practical implications in the interpolation methods for constructing the regional mean sea surface model in the eastern Mediterranean Sea
- Validation of a tailored gravity field model for precise quasigeoid modelling over selected sites in Cameroon and South Africa
- Evaluation of ML-based classification algorithms for GNSS signals in ocean environment
- Development of a hybrid geoid model using a global gravity field model over Sri Lanka
- Implementation of GAGAN augmentation on smart mobile devices and development of a cooperative positioning architecture
- On the GPS signal multipath at ASG-EUPOS stations
