Abstract
In this paper, a machine-learning-based system that could provide automated short-term solar flare prediction is presented. This system accepts two sets of inputs: McIntosh classification of sunspot groups and solar cycle data. In order to establish a correlation between solar flares and sunspot groups, the system explores the publicly available solar catalogues from the National Geophysical Data Center to associate sunspots with their corresponding flares based on their timing and NOAA numbers. The McIntosh classification for every relevant sunspot is extracted and converted to a numerical format that is suitable for machine learning algorithms. Using this system we aim to predict whether a certain sunspot class at a certain time is likely to produce a significant flare within six hours time and if so whether this flare is going to be an X or M flare. Machine learning algorithms such as Cascade-Correlation Neural Networks (CCNNs), Support Vector Machines (SVMs) and Radial Basis Function Networks (RBFN) are optimised and then compared to determine the learning algorithm that would provide the best prediction performance. It is concluded that SVMs provide the best performance for predicting whether a McIntosh classified sunspot group is going to flare or not but CCNNs are more capable of predicting the class of the flare to erupt. A hybrid system that combines a SVM and a CCNN is suggested for future use.
Similar content being viewed by others
References
Acir, N., Guzelis, C.: 2004, Expert. Syst. Appl. 27, 451.
Benkhalil, A., Zharkova, V., Ipson, S., Zharkov, S.: 2003, In: Holstein, H., Labrosse, F. (eds.) AISB’03 Symposium on Biologically-Inspired Machine Vision, Theory and Application, University of Wales, Aberystwyth.
Bishop, C.M.: 1995, Neural Networks for Pattern Recognition, Oxford University Press, London, p. 164.
Borda, R.A.F., Mininni, P.D., Mandrini, C.H., Gomez, D.O., Bauer, O.H., Rovira, M.G.: 2002, Solar Phys. 206, 347.
Bornmann, P.L., Shaw, D.: 1994, Solar Phys. 150, 127.
Broomhead, D.S., Lowe, D.: 1988, Complex Syst. 2, 321.
Calvo, R.A., Ceccatto, H.A., Piacentini, R.D.: 1995, Astrophys. J. 444, 916.
Distante, C., Ancona, N., Siciliano, P.: 2003, Sens. Actuators B: Chem. 88, 30.
Fahlmann, S.E., Lebiere, C.: 1989, In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems 2 (NIPS-2), Morgan Kaufmann, Denver, p. 524.
Frank, R.J., Davey, N., Hunt, S.P.: 1997, J. Intell. Robot. Syst. 31, 91.
Fukunaga, K.: 1990, Introduction to Statistical Pattern Recognition, Academic, New York, p. 220.
Gallagher, P.T., Moon, Y.J., Wang, H.M.: 2002, Solar Phys. 209, 171.
Gao, J.L., Wang, H.M., Zhou, M.C.: 2002, Solar Phys. 205, 93.
Greatrix, G.R., Curtis, G.H.: 1973, Observatory 93, 114.
Hale, G.E., Ellerman, F., Nicholson, S.B., Joy, A.H.: 1919, Astrophys. J. 49, 153.
Hathaway, D., Wilson, R.M., Reichmann, E.J.: 1994, Solar Phys. 151, 177.
Huang, Z., Chen, H.C., Hsu, C.J., Chen, W.H., Wu, S.S.: 2004, Decis. Support Syst. 37, 543.
Koskinen, H., Eliasson, L., Holback, B., Andersson, L., Eriksson, A., Mälkki, A., Norberg, O., Pulkkinen, T., Viljanen, A., Wahlund, J.-E., Wu, J.-G.: 1999, Space Weather and Interactions with Spacecraft, Finnish Meteorological Institute Reports 1999-4.
Künzel, H.: 1960, Astron. Nachr. 285, 271.
Lantos, P.: 2006, Solar Phys. 236, 199.
Lefebvre, S., Rozelot, J.P.: 2004, Solar Phys. 219, 25.
Liu, C., Deng, N., Liu, Y., Falconer, D., Goode, P.R., Denker, C., Wang, H.M.: 2005, Astrophys. J. 622, 722.
Manik, A., Singh, A., Yan, S.: 2004, In: Berkowitz, E.G. (ed.) Fifteenth Midwest Artificial Intelligence and Cognitive Sciences Conference, Omnipress, Chicago, p. 74.
McIntosh, P.S.: 1990, Solar Phys. 125, 251.
Pal, M., Mather, P.M.: 2004, Futur. Gener. Comput. Syst. 20, 1215.
Pap, J., Bouwer, S., Tobiska, W.: 1990, Solar Phys. 129, 165.
Qahwaji, R., Colak, T.: 2006a, Int. J. Comput. Appl. 13, 9.
Qahwaji, R., Colak, T.: 2006b, In: Chu, H.W., Aguilar, J., Rishe, N., Azoulay, J. (eds.) The Third International Conference on Cybernetics and Information Technologies, Systems and Applications, International Institute of Informatics and Systemics, Orlando, p. 192.
Qu, M., Shih, F.Y., Jing, J., Wang, H.M.: 2003, Solar Phys. 217, 157.
Sakurai, K.: 1970, Planet. Space Sci. 18, 33.
Sammis, I., Tang, F., Zirin, H.: 2000, Astrophys. J. 540, 583.
Schetinin, V.: 2003, Neural Process. Lett. 17, 21.
Shet, R.N., Lai, K.H., Edirisinghe, E., Chung, P.W.H.: 2005, In: Marques, J.S., de la Pe’rez, B.N., Pina, P. (eds.) Pattern Recognition and Image Analysis, Lecture Notes in Computer Science, vol. 3523, Springer, Berlin, p. 343.
Shi, Z.X., Wang, J.X.: 1994, Solar Phys. 149, 105.
Shih, F.Y., Kowalski, A.J.: 2003, Solar Phys. 218, 99.
Smieja, F.J.: 1993, Circuits Syst. Signal Process. 12, 331.
Sutton, R.S., Barto, A.G.: 1998, Reinforcement Learning: An Introduction, MIT, Cambridge, p. 193.
Ternullo, M., Contarino, L., Romano, P., Zuccarello, F.: 2006, Astron. Nachr. 327, 36.
Turmon, M., Pap, J.M., Mukhtar, S.: 2002, Astrophys. J. 568, 396.
Vapnik, V.: 1999, The Nature of Statistical Learning Theory, Springer, New York, p. 138.
Veronig, A., Temmer, M., Hanslmeier, A., Otruba, W., Messerotti, M.: 2002, Astron. Astrophys. 382, 1070.
Wang, H., Qu, M., Shih, F., Denker, C., Gerbessiotis, A., Lofdahl, M., Rees, D., Keller, C.: 2003, Bull. Am. Astron. Soc. 36, 755.
Warwick, C.S.: 1966, Astrophys. J. 145, 215.
Wheatland, M.S.: 2004, Astrophys. J. 609, 1134.
Zharkova, V., Ipson, S., Benkhalil, A., Zharkov, S.: 2005, Artif. Intell. Rev. 23, 209.
Zharkova, V., Schetinin, V.: 2003, In: Jain, L.C., Howlett, R.J., Palade, V. (eds.) Proceedings of the Seventh International Conference on Knowledge-Based Intelligent Information and Engineering Systems KES’03, Springer, Oxford, p. 148.
Zirin, H., Liggett, M.A.: 1987, Solar Phys. 113, 267.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Qahwaji, R., Colak, T. Automatic Short-Term Solar Flare Prediction Using Machine Learning and Sunspot Associations. Sol Phys 241, 195–211 (2007). https://doi.org/10.1007/s11207-006-0272-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11207-006-0272-5