GPS-Toplam Elektron İçeriği Tahmininde Regresyon Modellerinin Performansının Karşılaştırılması

Öz

İyonosfer, üst atmosferde radyo iletişiminin sağlandığı önemli bir katmandır. İyonosfer atmosferin 50 km ila 1000 km yüksekliği boyunca yer alır. İyonosferin en önemli parametresi olan elektron yoğunluğu, konuma, zamana, mevsimlere, yüksekliğe, güneş, jeomanyetik ve sismik aktiviteye bağlı olarak değişir. Elektron yoğunluğunun ölçülebilir önemli bir miktarı, iyonosferin ve üst atmosferin yapısını araştırmak için kullanılan Toplam Elektron İçeriği’dir (TEİ). TEİ kestiriminde, düşük maliyetli ve yaygın alıcı ağına sahip olan Yerküresel Konumlama Sistemi (YKS) yaygın olarak kullanılır. Bu çalışmada YKS’den kestirilen IONOLAB-TEC verileri kullanılmıştır. TEİ'nin tahmini, Dünya-uzay ve uydudan uyduya iletişim sistemlerini çalıştırmak ve planlamak, TEİ kullanarak deprem haberci sinyallerini oluşturmak ve iyonosferdeki anomalileri tespit etmek için önemli bir olgudur. Bu çalışmada, YKS’den elde edilen IONOLAB-TEC verileri, regresyon modelleri kullanılarak tahmin edilmiştir. Test edilen algoritmalar arasında, Üstel Gauss Süreç Regresyon ve Etkileşimli Lineer Regresyon algoritmalarının, TEC tahmini için oldukça başarılı ve yüksek performanslı bir modeller olduğu gözlenmiştir.  

Anahtar Kelimeler

• Toplam elektron içeriği
• makine öğrenmesi
• tahmin
• regresyon
• Total electron content
• machine learning
• prediction
• regression

Comparison of the Performance of the Regression Models in GPS-Total Electron Content Prediction

Öz

The ionosphere is an important layer that provides radio communication in the upper atmosphere. The ionosphere is located between 50 km and 1000 km above the atmosphere. Electron density, which is the most important parameter of the ionosphere, changes depending on location, time, seasons, altitude, solar, geomagnetic and seismic activity. A significant measurable amount of electron density is Total Electron Content (TEC), which is used to probe the structure of the ionosphere and upper atmosphere. The Global Positioning System (GPS), which has a low cost and widespread receiver network is prominent used in TEC estimation. The IONOLAB-TEC data estimated from GPS is used in this study. Prediction of TEC is important phenomenon to operate and to plan the Earth-space and satellite-to-satellite communication systems, to generate the earthquake precursor signals using TEC and to detect of anomalies in the ionosphere. In this study, IONOLAB-TEC data obtained from GPS is estimated using regression models. Among the tested algorithms, it is observed that the Exponential Gaussian Process Regression and Interactions Linear Regression algorithms are very successful and high-performance models for TEC estimation.

Anahtar Kelimeler

• Total electron content
• machine learning
• prediction
• regression

Kaynakça

1. [1] Hagen, J.B., "Radio-Frequency Electronics: Circuits and Applications", Cambridge University Press, (2009).
2. [2] Rishbeth, H., Garriott, O.K., "Introduction to Ionospheric Physics", Academic Press, (1969).
3. [3] Unal, I., Karatay, S., Yesil, A., Hancerliogullari, A., "Seasonal Variations of Impedance in the Ionospheric Plasma", Journal of Polytechnic, 23(2):427-433, (2020).
4. [4] Hofmann-Wellenhof, B., Lichtenegger, H., Collins, J., "Global Positioning System Theory and Practice", Springer-Verlag, (1997).
5. [5] Arikan, F., Erol, C.B., Arikan, O., "Regularized estimation of vertical total electron content from Global Positioning System data", Space Physics, 108(A12):1-12, (2003).
6. [6] Arikan, F., Nayir, H., Sezen, U., Arikan, O., "Estimation of single station interfrequency receiver bias using GPS-TEC", Radio Science, 43(4):1-13, (2008).
7. [7] Zhang, B., Niu, J., Li, W., Shen, Y., Wu, T., Yang, W., Deng, W., "A single station ionospheric empirical model using GPS-TEC observations based on nonlinear least square estimation method", Advances in Space Research, 68(9):3821-3834, (2021).
8. [8] Li, W., Zhao, D., He, C., Shen, Y., Hu, A. Zhang, K., "Application of a Multi-Layer Artificial Neural Network in a 3-D Global Electron Density Model Using the Long-Term Observations of COSMIC, Fengyun- 3C, and Digisonde", Space Weather, 19(3):1-19, (2021).

9. [9] Zhao, D., Wang, L., Chendong, L., Hancock, C.M., Roberts, G.W., Wang, Q., "Analysis on the ionospheric scintillation monitoring performance of ROTI extracted from GNSS observations in high-latitude regions", Advances in Space Research, 69(1):142-158, (2022).
10. [10] Li, W., Zhao, D., He, C., Hancock, C.M., Shen, Y., Zhang, K., "Spatial-Temporal Behaviors of Large-Scale Ionospheric Perturbations During Severe Geomagnetic Storms on September 7–8 2017 Using the GNSS, SWARM and TIE-GCM Techniques", Journal of Geophysical Research Space Physics, 127(3):1-21, (2022).
11. [11] Zhao, D., Li, W., Li, C., Tang, X., Wang, Q., Hancock, C.M., Roberts, G.W., Zhang, K., "Ionospheric Phase Scintillation Index Estimation Based on 1 Hz Geodetic GNSS Receiver Measurements by Using Continuous Wavelet Transform", Space Weather, 20(4):1-18, (2022).
12. [12] Karatay, S., "Estimation of frequency and duration of ionospheric disturbances over Turkey with IONOLAB-FFT algorithm", Journal of Geodesy, 94(89):1-24, (2020).
13. [13] Karatay, S., "Detection of the ionospheric disturbances on GPS-TEC using Differential Rate Of TEC (DROT) algorithm", Advances in Space Research, 65(10):2372-2390, (2020).
14. [14] Karatay, S., Cinar, A., Arikan, F., "Ionospheric responses during equinox and solstice periods over Turkey", Advances in Space Research, 60(9):1958-1967, (2017).
15. [15] Sayin, I., Arikan, F., Arikan, O., "Regional TEC mapping with Random Field Priors and Kriging", Radio Science, 43(5):1-14, (2008).
16. [16] Mukesh, R., Karthikeyan, V., Soma, P., Sindhu, P., "Ordinary kriging-and cokriging -based surrogate model for ionospheric TEC prediction using NavIC/GPS data", Acta Geophysica, 68:1529–1547, (2020).
17. [17] Suraj, P.S., Kumar Dabbakuti, J.R.K. V. R. Chowdhary, J.R.K., Tripathi, N.K., Ratnam, D.V., "Linear time series modeling of GPS-derived TEC observations over the Indo-Thailand region", Journal of Geodesy, 92:863–872, (2018).
18. [18] Zhang, M.L., Liu, C., Wan, W., Liu, L., Ning, B., "A global model of the ionospheric F2 peak height based on EOF analysis", Annales Geophysicae, 27(2009):3203-3212, (2009).
19. [19] Akyol, A., Arikan, O., Arikan, F., "A Machine Learning-Based Detection of Earthquake Precursors Using Ionospheric Data", Radio Science, 55(11):1-21, (2020).
20. [20] Lean, J.L., Meier, R.R., Picone, J.M.,. Emmert, J.T., "Ionospheric total electron content: Global and hemispheric climatology", Journal of Geophysical Research Space Physics, 116(A10):1-18, (2011).
21. [21] Lean, J.L., Emmert, J.T., Picone, J.M., Meier, R.R., "Global and regional trends in ionospheric total electron content", Journal of Geophysical Research Space Physics, 116(A2):1-11, (2011).
22. [22] Arikan, F., Erol, C.B., Arikan, O., "Regularized estimation of vertical total electron content from GPS data for a desired time period", Radio Science, 39(6):1-10, (2004).
23. [23] Nayir, H., Arikan, F., Arikan, O., Erol, C.B., "Total Electron Content Estimation with Reg-Est", Journal of Geophysical Research Space Physics, 112(A11):1-10, (2007).
24. [24] IONOLAB, www.ionolab.org, (2022).
25. [25] United States Geological Survey, https://www.usgs.gov/programs/earthquake-hazards/earthquakes, (2022).
26. [26] International GNSS Service, https://igs.org/network/, (2022).
27. [27] Weisberg, S., "Applied Linear Regression", John Wiley and Sons. Inc., (2005).
28. [28] Yasar, Y., Yavasca, S., Yasar, C., "Long term electric peak load forecasting of Kutahya using different approaches", International Journal on Technical and Physical Problems of Engineering, 3(2):87-91, (2011).
29. [29] Rokach, L., Maimon, O., "Top-Down Induction of Decision Trees Classifiers—A Survey", IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 5(4):476-487, (2005).
30. [30] Lin, S.L., "Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults", Electronics, 10(18):1-22, (2021).
31. [31] Taki, M., Rohani, A., Soheili-Fard, F., Abdeshahi, A., "Assessment of energy consumption and modeling of output energy for wheat production by neural network (MLP and RBF) and Gaussian process regression (GPR) models", Journal of Cleaner Production, 172:3028-3041, (2018).
32. [32] Hyndman, R.J., Koehlerb, A.B., "Another look at measures of forecast accuracy", International Journal of Forecasting, 22(4):679-688, (2006).
33. [33] Erken, F., Karatay, S., Cinar, A., "Spatio-Temporal Prediction of Ionospheric Total Electron Content Using an Adaptive Data Fusion Technique", Geomagnetism and Aeronomy, 59:971–979, (2019).
34. [34] Glantz, S., Slinker, B., Neilands, T., "Primer of Applied Regression & Analysis of Variance", McGraw Hill, (2016).
35. [35] Willmott, C.J., Matsuura, K., "Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance", Climate Research, 30:79–82, (2005).