Abstract
The paper explores the possibilities of using data classification methods when forecasting time series of the geomagnetic Kp-index by machine learning methods. To classify categories of the Kp-index based on the degree of disturbance, linear and logistic regression, random forest, gradient boosting on top of decision trees, and artificial neural networks of various architectures are used. The results of these methods are compared with a trivial inertial forecast (the statistical indicators of which for problems of this type are always high) at horizons from 3 h to 1 day in 3-h increments. The problem of choosing a cross-validation scheme for selecting the model hyperparameters, ways to overcome the imbalance of categories, the relative importance of input features, as well as the dependence of the results on the test sample (beginning of the 25th solar activity cycle) on inclusion in the training sample of data from the 23rd and 24th cycles or only the 24th cycles are studied. Based on the results, conclusions are drawn about the preferred methods for classifying values of the Kp-index based on the level of geomagnetic disturbance. Ways for further research and possible improvement of the classification quality are outlined, including for determining the characteristic hidden states of Earth’s magnetosphere as a dynamic system in order to improve the quality of forecasting geomagnetic indices.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1134%2FS0016793224600140/MediaObjects/11478_2024_8823_Fig9_HTML.png)
Similar content being viewed by others
REFERENCES
ACE Browse Hourly Averages. https://izw1.caltech.edu/ cgi-bin/dib/rundibviewbr/ACE/ASC/DATA/browse-data?ACE_BROWSE.HDF!hdfref;tag=1962,ref=3,s=0.
Akasofu, S.-I. and Chapman, S., Solar–Terrestrial Physics, Oxford: Clarendon Press, 1972.
Bala, R. and Reiff, P., Improvements in short-term forecasting of geomagnetic activity, Space Weather, 2012, vol. 10, no. 6, p. S06001. https://doi.org/10.1029/2012SW000779
Bartels, J.R., The standardized index, Ks and the planetary index, Kp, IATME Bull., 1949, vol. 12b, pp. 97–120.
Bartels, J., Heck, N.H., and Johnson, H.F., The three-hour-range index measuring geomagnetic activity, J. Geophys. Res., 1939, vol. 44, no. 4, pp. 411–454. https://doi.org/10.1029/TE044i004p00411
Belakhovsky, V.B., Pilipenko, V.A., Sakharov, Ya.A., and Selivanov, V.N., The growth of geomagnetically induced currents during CME and CIR geomagnetic storms in 2021, Bull. Russ. Acad. Sci.: Phys., 2023, vol. 87, no. 2, pp. 236–242. https://doi.org/10.3103/S1062873822700988
Belov, A.V., Villoresi, G., Dorman, L.I., et al., Effect of the space on operation of satellites, Geomagn. Aeron. (Engl. Transl.), 2004, vol. 44, no. 4, pp. 461–468.
Boberg, F., Wintoft, P., and Lundstedt, H., Real time Kp predictions from solar wind data using neural networks, Phys. Chem. Earth, Part C: Sol., Terr. Planet. Sci., 2000, vol. 25, no. 4, pp. 275–280. https://doi.org/10.1016/S1464-1917(00)00016-7
Boroyev, R.N., Vasiliev, M.S., and Baishev, D.G., The relationship between geomagnetic indices and the interplanetary medium parameters in magnetic storm main phases during CIR and ICME events. J. Atmos. Sol.-Terr. Phys., 2020, vol. 204, p. 105290. https://doi.org/10.1016/j.jastp.2020.105290
Breiman, L., Random forests, Mach. Learn., 2001, vol. 45, pp. 5–32. https://doi.org/10.1023/A:1010933404324
Chawla, N.V., Bowyer, K.W., Hall, L.O., and Kegelmeyer, W.P., SMOTE: Synthetic minority over-sampling technique, J. Artif. Intell. Res., 2002, vol. 16, pp. 321–357. https://doi.org/10.1613/jair.953
Cho, K., van Merriënboer, B., Bahdanau, D., and Bengio, Y., On the properties of neural machine translation: encoder–decoder approaches, in Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, Association for Computational Linguistics, 2014, pp. 103–111. https://doi.org/10.3115/v1/W14-4012.
Cole, D.G., Space weather: its effects and predictability, Space Sci. Rev., 2003, vol. 107, pp. 295–302. https://doi.org/10.1023/A:1025500513499
Cox, D.R., The regression analysis of binary sequences, J. R. Stat. Soc.: Ser. B (Methodol.), 1958, vol. 20, no. 2, pp. 215–242. https://www.nuffield.ox.ac.uk/users/cox/cox48.pdf.
Daglis, I.A., Space Storms and Space Weather, Dordrecht: Kluwer, 2001. https://doi.org/10.1007/978-94-010-0983-6
Dolenko, S.A., Orlov, Yu.V., Persiantsev, I.G., and Shugai, Ju.S., Neural network algorithm for events forecasting and its application to space physics data, Lect. Notes Comput. Sci., 2005, vol. 3697, pp. 527‒532. https://doi.org/10.1007/11550907_83
Dolenko, S.A., Myagkova, I.N., Shiroky, V.R., and Persiantsev, I.G., Objective discrimination of geomagnetic disturbances and prediction of Dst index by artificial neural networks, in Proc. 10th International Conference “Problems of Geocosmos”, St. Petersburg, 2014, pp. 270–275.
Dolenko, S.A., Myagkova, I.N., and Persiantsev, I.G., The use of artificial neural network segmentation of multivariate time series for the analysis of geomagnetic disturbances, Moscow Univ. Phys. Bull., 2016, vol. 71, no. 4, pp. 454–463.
Efitorov, A.O., Myagkova, I.N., Shirokii, V.R., and Dolenko, S.A., The prediction of the Dst-index based on machine learning methods, Cosmic Res., 2018, vol. 56, no. 6, pp. 434–441. https://doi.org/10.1134/S0010952518060035
Elliott, H.A., Jahn, J.-M., and McComas, D.J., The Kp index and solar wind speed relationship: insights for improving space weather forecasts, Space Weather, 2013, vol. 11, pp. 339–349. https://doi.org/10.1002/swe.20053
Ermolaev, Yu.I. and Ermolaev, M.Yu., Solar and interplanetary sources of geomagnetic storms: Space weather aspects, Geofiz. Protsessy Biosfera, 2009, vol. 8, no. 1, pp. 5–35.
Friedman, J.H., Greedy function approximation: a gradient boosting machine, Ann. Stat., 2002, vol. 29, no. 5, pp. 1189–1232.
Gadzhiev, I., Myagkova, I., and Dolenko, S., Use of classification algorithms to predict the grade of geomagnetic disturbance, in Advances in Neural Computation, Machine Learning, and Cognitive Research VI: NEUROINFORMATICS 2022, Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., and Tiumentsev, Y., Eds., Cham, Springer, 2023, vol. 1064, pp. 426–435. https://doi.org/10.1007/978-3-031-19032-2_44.
Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural. Comput., 1997, vol. 9, no. 8, pp. 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hoerl, A.E. and Kennard, R.W., Ridge regression: Biased estimation to nonorthogonal problems, Technometrics, 1970, vol. 12, pp. 56–67.
Iucci, N., Levitin, A.E., Belov, A.V., et al., Space weather conditions and spacecraft anomalies in different orbits, Space Weather, 2005, vol. 3, no. 1, p. S01001. https://doi.org/10.1029/2003SW000056
Ji, E. Y., Moon, Y. J., Park, J., Lee, J. Y., and Lee, D. H., Comparison of neural network and support vector machine methods for Kp forecasting, J. Geophys. Res.: Space Phys., 2013, vol. 118, pp. 5109–5117. https://doi.org/10.1002/jgra.50500
Kalegaev, V.V., Alekseev, I.I., and Kropotkin, A.P., Magnetic storms in the magnetosphere and substorms. http://nuclphys.sinp.msu.ru/magn/index.html.
Kataoka, R. and Miyoshi, Y., Average profiles of the solar wind and outer radiation belt during the extreme flux enhancement of relativistic electrons at geosynchronous orbit, Ann. Geophys., 2008, vol. 26, pp. 1335–1339.https://doi.org/10.5194/angeo-26-1335-2008
Ke, G., Q. Meng, T. Finley, et al., LightGBM: A highly efficient gradient boosting decision tree, Adv. Neural Inf. Process. Syst., 2017, vol. 30, pp. 3149–3157.
Kingma, D.P. and Ba, J., Adam: a method for stochastic optimization, in Proceedings of International Conference on Learning Representations, 2015. https://doi.org/10.48550/ar**v.1412.6980
Kudela, K., Space weather near Earth and energetic particles: Selected results, J. Phys.: Conf. Ser., 2013, vol. 409, no. 1, p. 012017. https://doi.org/10.1088/1742-6596/409/1/012017
Lazutin, L.L., Mirovye i polyarnye magnitnye buri (Worldwide and Polar Magnetic Storms), Moscow: MGU, 2012.
McGranaghan, R.M., Camporeale, E., Georgoulis, M., and Anastasiadis, A., Space weather research in the Digital Age and across the full data lifecycle: Introduction to the topical issue, J. Space Weather Space Clim., 2021, vol. 11, p. 50. https://doi.org/10.1051/swsc/2021037
Myagkova, I.N. and Dolenko, S.A., Comparative analysis of the quality of prediction for fluences of relativistic electrons of the outer radiation belt of the Earth at different phases of the solar activity cycle, in Proceedings of the 11th International Conference “Problems of Geocosmos”, St. Petersburg, 2016, p. 79.
Myagkova, I.N., Shugay, Yu.S., Veselovsky, I.S., and Yakovchouk, O.S., Comparative analysis of recurrent high-speed solar wind streams influence on the radiation environment of near-Earth space in April–July 2010, Sol. Syst. Res., 2013, vol. 47, no. 2, pp. 141–155. https://doi.org/10.1134/S0038094613020068
Myagkova, I., Shiroky, V., and Dolenko, S., Prediction of geomagnetic indexes with the help of artificial neural networks, in VIII International Conference “Solar-Terrestrial Relations and Physics of Earthquake Precursors” (E3S Web of Conferences), 2017, vol. 20, p. 02011. https://doi.org/10.1051/e3sconf/20172002011
Nishida, A., Geomagnetic Diagnosis of the Magnetosphere, New York: Springer, 1978. https://doi.org/10.1093/gji/61.3.680
Prokhorenkova, L., G. Gusev, A. Vorobev, et al., CatBoost: Unbiased boosting with categorical features, in 32nd Conference on Neural Information Processing Systems, Montreal, 2019, pp. 6638–6648. https://doi.org/10.48550/ar**v.1706.09516
Qiu, Q., Fleeman, J.A., and Ball, D.R., Geomagnetic disturbance: A comprehensive approach by American electric power to address the impacts, IEEE Elect. Mag., 2015, vol. 3, no. 4, pp. 22–33. https://doi.org/10.1109/MELE.2015.2480615
Romanova, N.V., Pilipenko, V.A., Yagova, N.V., and Belov, A.V., Statistical correlation of the rate of failures on geosynchronous satellites with fluxes of energetic electrons and protons, Cosmic Res., 2005, vol. 43, no. 3, pp. 179–185.
Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al., Learning internal representations by error propagation, in Paralleled Distributed Processing, Cambridge: MIT Press, 1986, vol. 1, pp. 318–362.
Schrijver, C.J., Kauristie, K., Aylward, A.D., et al., Understanding space weather to shield society: A global road map for 2015–2025 commissioned by COSPAR and ILWS, Adv. Space Res., 2015, vol. 55, no. 12, pp. 2745–2807. https://doi.org/10.1016/j.asr.2015.03.023
Tan, Y., Hu, Q., Wang, Z., and Zhong, Q., Geomagnetic index Kp forecasting with LSTM, Space Weather, 2018, vol. 16, pp. 406–416. https://doi.org/10.1002/2017SW001764
Vassiliadis, D., Forecasting space weather, in Space Weather: Physics and Effects, Berlin: Springer, 2007, pp. 403–425. https://doi.org/10.1007/978-3-540-34578-7_14
Wang, J., Zhong, Q., Liu, S., Miao, J., Liu, F., Li, Z., and Tang, W., Statistical analysis and verification of 3-hourly geomagnetic activity probability predictions., Space Weather, 2015, vol. 13, pp. 831–852. https://doi.org/10.1002/2015SW001251
World Data Center for Geomagnetism, Kyoto. http://wdc.kugi.kyoto-u.ac.jp.
Funding
The study was supported by the Russian Science Foundation, grant no. 23-21-00237 (https://rscf.ru/en/project/23-21-00237/).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gadzhiev, I.M., Barinov, O.G., Myagkova, I.N. et al. Using Classification Methods in Forecasting the Level of Geomagnetic Field Disturbance Based on the Kp-Index. Geomagn. Aeron. 64, 415–426 (2024). https://doi.org/10.1134/S0016793224600140
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0016793224600140