İyonosfer Parametrelerinin Çok Katmanlı Algılayıcılar ile Kestirimi

Year 2021, , 1480 - 1494, 30.09.2021

Muzaffer Can İban , Erman Şentürk

https://doi.org/10.31202/ecjse.948557

Cited By: 1

Abstract

İyonosferik parametrelerin değişimi, uzay iklimi, haberleşme ve seyrüsefer konularındaki çalışmalarda oldukça önemli bir role sahiptir. Bu çalışmada, derin öğrenme yöntemlerinden olan Çok Katmanlı Algılayıcılar (ÇKA) regresyonu modelinin F2 katmanı kritik frekansı (foF2), tepe elektron yoğunluğunun F2 katmanı yüksekliği (hmF2) ve toplam elektron içeriği (TEC) gibi iyonosfer parametrelerini kestirim performansı analiz edilmiştir. 1 Ocak 2012 ile 31 Aralık 2013 tarihleri arasında, ROME (RO041) digisonde istasyonunun saatlik f0F2 ve hmF2 değerleri ile M0SE00ITA istasyon kodlu Uluslararası GNSS Servisi (IGS) istasyonunun saatlik TEC değerleri kullanılmıştır. Her iki istasyon da birbirine oldukça yakındır ve orta enlem bölgesinde bulunmaktadır. Önerilen yöntemde eğitilecek olan girdi parametreleri, verilerin gözlem periyotları, F10.7 güneş indeksi, jeomanyetik Ap indeksinin saatlik değerleri ve mevcut (t) zamanındaki f0F2, hmF2 ve TEC değerleri ile bunların bir önceki güne ait (t-23) değerleri olarak seçilmiştir. Çıktı değişken ise, bu parametrelerin bir saat ileri (t+1) tahmin değerleridir. 2012 yılına ait veriler, bu modelin eğitilmesi için kullanılmıştır. 2013 yılı verileri üzerinde gerçekleştirilen tahmin çalışmalarının doğruluğu için ortalama kök karesel hata ve korelasyon değerleri hesaplanmış olup, bu değerler tüm yıl, yaz, kış ve ekinoks dönemleri için ayrı ayrı karşılaştırılmıştır. Sonuçlar, önerilen regresyon modelinin kestirim performansının genellikle Kış döneminde daha yüksek, yaz döneminde ise diğer dönemlere görece düşük olduğunu göstermiştir. Analiz edilen tüm dönemlerde elde edilen istatistiksel sonuçlara göre, modelin çoklu iyonosferik parametrelerin tahmininde genel anlamda başarılı olduğu tespit edilmiştir.

Keywords

iyonosferik parametre kestirimi, derin öğrenme, çok katmanlı algılayıcı

The Prediction of Ionospheric Parameters Using Multi-layer Perceptrons

Abstract

The variation of the ionospheric parameters has a crucial role in space weather, communication, and navigation applications. In this research, we analyze the prediction performance of multi-layer perceptron (MLP) regression model, which is one of deep learning algorithms, for the F2-layer critical frequency (f0F2), F2-layer height of the peak electron density (hmF2), and total electron content (TEC). The hourly f0F2 and hmF2 values of ROME (RO041) digisonde and hourly TEC values of an International GNSS Service (IGS) station with site code M0SE00ITA were obtained for the period between January 1, 2012 and 31 December 2013. Both stations are located in the mid-latitude region and are very close to each other. The inputs to be trained in the proposed methods are the observation periods of the data, hourly values of solar index F10.7 and geomagnetic index Ap, the present values of f0F2(t), hmF2(t), TEC(t), and their values at t−23h as separately. The output is the predicted values of parameters at t + 1. The 2012 values of these parameters were used to train the models and they were predicted 1 hour in advance during 2013. The root mean square error (RMSE) and correlation values between observed and predicted data were compared for the whole year, summer, winter, and equinox periods. The results showed that the prediction performance of the proposed regression model is generally higher in the Winter period and lower in the summer period than the other periods. The statistical results obtained in all analyzed periods shown that the model was generally successful in forecasting multiple ionospheric parameters.

Keywords

Ionospheric parameter prediction, deep learning, multi-layer perceptron

References

• Davies, K., Ionospheric Radio. London: Peter Peregrinus, 1990.
• Fayyaz, M., Naqvi, N. A., “The trends/ variations of Ionospheric parameters (hmF2, foF2) between observatory and International Reference Ionosphere web model values”, Fourth International Conference on Aerospace Science and Engineering (ICASE), 1–4.
• Li, M. vd., “Determination of the optimized single-layer ionospheric height for electron content measurements over China”, Journal of Geodesy, 2018, 92(2), 169–183
• Vaishnav, R., Jacobi, C., Berdermann, J., “Long-term trends in the ionospheric response to solar extreme-ultraviolet variations”, Annales Geophysicae, 2019, 37(6), 1141–1159
• Freeshah, M. vd., “Analysis of Atmospheric and Ionospheric Variations Due to Impacts of Super Typhoon Mangkhut (1822) in the Northwest Pacific Ocean”, Remote Sensing, 2021 13(4), 661
• Şentürk, E., Arqim Adil, M., Saqib, M., “Ionospheric total electron content response to annular solar eclipse on June 21, 2020”, Advances in Space Research, 2021, 67(6), 1937–1947
• Klobuchar, J., “Ionospheric Time-Delay Algorithm for Single-Frequency GPS Users”, IEEE Transactions on Aerospace and Electronic Systems, 1987, AES-23(3), 325–331
• Altinay, O., Tulunay, E., Tulunay, Y., “Forecasting of ionospheric critical frequency using neural networks”, Geophysical Research Letters, 1997, 24(12), 1467–1470
• Stanislawska, I., Zbyszynski, Z., “Forecasting of the ionospheric quiet and disturbed ƒ o F 2 values at a single location”, Radio Science, 2001, 36(5), 1065–1071
• Stanislawska, I., Zbyszynski, Z., “Forecasting of ionospheric characteristics during quiet and disturbed conditions”, Annals of Geophysics, 2002, 45(1), 169–175
• Chen, C., Wu, Z.-S., Ban, P.-P., Sun, S.-J., Xu, Z.-W., Zhao, Z.-W., “Diurnal specification of the ionospheric f 0 F 2 parameter using a support vector machine”, Radio Science, 2010, 45(5)
• Chen, C., Wu, Z., Sun, S., Ban, P., Ding, Z., Xu, Z., “Forecasting the ionospheric f0F2 parameter one hour ahead using a support vector machine technique”, Journal of Atmospheric and Solar-Terrestrial Physics, 2010, 72(18), 1341–1347
• Athieno, R., Jayachandran, P. T., Themens, D. R., “A neural network-based foF2 model for a single station in the polar cap”, Radio Science, 2017, 52(6), 784–796
• Fan, J., Liu, C., Lv, Y., Han, J., Wang, J., “A Short-Term Forecast Model of foF2 Based on Elman Neural Network”, Applied Sciences, 2019, 9(14), 2782
• Li, W., Zhao, D., He, C., Hu, A., Zhang, K., “Advanced Machine Learning Optimized by The Genetic Algorithm in Ionospheric Models Using Long-Term Multi-Instrument Observations”, Remote Sensing, 2020, 12(5), 866
• Alpaydin, E., Introduction to machine learning. Cambridge, Massachusetts: MIT Press, 2020.
• Géron, A., Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, 2019.
• Kramer, O., Machine Learning for Evolution Strategies 20. Cham: Springer International Publishing, 2016.
• Pedregosa, F. vd., “Scikit-learn: Machine learning in Python”, The Journal of Machine Learning Research, 2011, 12, 2825–2830
• Boden, M. A., The Philosophy of Artificial Intelligence. Oxford: Oxford University Press, 1990.
• Rosenblatt, F., “The perceptron: A probabilistic model for information storage and organization in the brain.”, Psychological Review, 1958, 65(6) ,386–408
• Hagan, M. T., Demuth, H. B., Jesús, O. De, “An introduction to the use of neural networks in control systems”, International Journal of Robust and Nonlinear Control, 2002, 12(11), 959–985
• Baum, E. B., “On the capabilities of multilayer perceptrons”, Journal of Complexity, 1988, 4(3) 193–215
• Tang, J., Deng, C., Huang, G.-B., “Extreme Learning Machine for Multilayer Perceptron”, IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(4), 809–821
• Kişi, Ö., “Streamflow Forecasting Using Different Artificial Neural Network Algorithms”, Journal of Hydrologic Engineering, 2007, 12(5), 532–539
• Maier, H. R., Dandy, G. C., “Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications”, Environmental Modelling & Software, 2000, 15(1), c. 15, 101–124,
• Du, K.-L., Swamy, M. N. S., “Multilayer Perceptrons: Architecture and Error Backpropagation”, Neural Networks and Statistical Learning, London: Springer London, 2014
• Chien-Cheng Yu, Bin-Da Liu, “A backpropagation algorithm with adaptive learning rate and momentum coefficient”, Proceedings of the 2002 International Joint Conference on Neural Networks, 2002, 1218–1223
• Fushiki, T., “Estimation of prediction error by using K-fold cross-validation”, Statistics and Computing, 2011, 21(2), 137–146
• Schratz, P., Muenchow, J., Iturritxa, E., Richter, J., Brenning, A., “Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data”, Ecological Modelling, 2019, 409, 109–120
• Williscroft, L.-A., Poole, A. W. V., “Neural networks, foF2, sunspot number and magnetic activity”, Geophysical Research Letters, 1996, 23(24), 3659–3662
• Afraimovich, E. L., Astafyeva, E. I., “TEC anomalies—Local TEC changes prior to earthquakes or TEC response to solar and geomagnetic activity changes?”, Earth, Planets and Space, 2008, 60(9), 961–966
• Şentürk, E., Çepni, M. S., “Ionospheric temporal variations over the region of Turkey: a study based on long-time TEC observations”, Acta Geodaetica et Geophysica, 2018, 53(4), 623–637
• Shichao Zhang, Qin, Z., Ling, C. X., Sheng, S., “‘Missing is useful’: missing values in cost-sensitive decision trees”, IEEE Transactions on Knowledge and Data Engineering, 2005, 17(12), 1689–1693
• Farhangfar, A., Kurgan, L., Dy, J., “Impact of imputation of missing values on classification error for discrete data”, Pattern Recognition, 2008, 41(12), 3692–3705
• Burdack, J., Horst, F., Giesselbach, S., Hassan, I., Daffner, S., Schöllhorn, W. I., “Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning”, Frontiers in Bioengineering and Biotechnology, 2020, 8
• Dey, S. K., Hossain, A., Rahman, M. M., “Implementation of a Web Application to Predict Diabetes Disease: An Approach Using Machine Learning Algorithm”, 21st International Conference of Computer and Information Technology (ICCIT), 2018
• Obaid, H. S., Dheyab, S. A., Sabry, S. S., “The Impact of Data Pre-Processing Techniques and Dimensionality Reduction on the Accuracy of Machine Learning”, 9th Annual Information Technology, Electromechanical Engineering and Microelectronics Conference (IEMECON), 2019