Automated Prediction of CMEs Using Machine Learning of CME – Flare Associations
- 190 Downloads
- 12 Citations
Abstract
Machine-learning algorithms are applied to explore the relation between significant flares and their associated CMEs. The NGDC flares catalogue and the SOHO/LASCO CME catalogue are processed to associate X and M-class flares with CMEs based on timing information. Automated systems are created to process and associate years of flare and CME data, which are later arranged in numerical-training vectors and fed to machine-learning algorithms to extract the embedded knowledge and provide learning rules that can be used for the automated prediction of CMEs. Properties representing the intensity, flare duration, and duration of decline and duration of growth are extracted from all the associated (A) and not-associated (NA) flares and converted to a numerical format that is suitable for machine-learning use. The machine-learning algorithms Cascade Correlation Neural Networks (CCNN) and Support Vector Machines (SVM) are used and compared in our work. The machine-learning systems predict, from the input of a flare’s properties, if the flare is likely to initiate a CME. Intensive experiments using Jack-knife techniques are carried out and the relationships between flare properties and CMEs are investigated using the results. The predictive performance of SVM and CCNN is analysed and recommendations for enhancing the performance are provided.
Keywords
CMEs prediction Machine learning Solar flares Space weather CME Neural networks Support vector machinesPreview
Unable to display preview. Download preview PDF.
References
- Acir, N., Guzelis, C.: 2004, Expert Syst. Appl. 27, 451. CrossRefGoogle Scholar
- Borda, R.A.F., Mininni, P.D., Mandrini, C.H., Gomez, D.O., Bauer, O.H., Rovira, M.G.: 2002, Solar Phys. 206, 347. CrossRefADSGoogle Scholar
- Cliver, E.W., Hudson, H.S.: 2002, J. Atmos. Solar-Terr. Phys. 64, 231. CrossRefADSGoogle Scholar
- Colak, T., Qahwaji, R.: 2007, Adv. Soft Comput. 39, 316. CrossRefGoogle Scholar
- Distante, C., Ancona, N., Siciliano, P.: 2003, Sens. Actuator B-Chem. 88, 30. CrossRefGoogle Scholar
- Fawcett, T.: 2006, Pattern Recognit. Lett. 27, 861. CrossRefGoogle Scholar
- Fukunaga, K.: 1990, Introduction to Statistical Pattern Recognition, Academic, New York. MATHGoogle Scholar
- Gosling, J.T.: 1995, J. Geophys. Res. 100, 7921. CrossRefADSGoogle Scholar
- Huang, Z., Chen, H.C., Hsu, C.J., Chen, W.H., Wu, S.S.: 2004, Decis. Support Syst. 37, 543. CrossRefGoogle Scholar
- Koskinen, H., Tanskanen, E., Pirjola, R., Pulkkinen, A., Dyer, C., Rogers, D., Cannon, P., Menville, J., Boscher, D.: 2001, Space Weather Effects Catalogue, Finnish Meteorological Inst., Helsinki. Google Scholar
- Kurokawa, H.: 2002, Commun. Res. 49, 49. Google Scholar
- Lenz, D.: 2004, Ind. Phys. 9, 18. Google Scholar
- Lin, R.P., Hudson, H.S.: 1976, Solar Phys. 50, 153. CrossRefADSGoogle Scholar
- Pal, M., Mather, P.M.: 2004, Fut. Gener. Comput. Syst. 20, 1215. CrossRefGoogle Scholar
- Qahwaji, R., Colak, T.: 2006, Comput. Appl. 13, 9. Google Scholar
- Qahwaji, R., Colak, T.: 2007, Solar Phys. 241, 195. CrossRefADSGoogle Scholar
- Qu, M., Shih, F.Y., Jing, J., Wang, H.M.: 2003, Solar Phys. 217, 157. CrossRefADSGoogle Scholar
- Tousey, R.: 1973, Adv. Space Res. 13, 713. Google Scholar
- Webb, D.F.: 2000, J. Atmos. Solar-Terr. Phys. 62, 1415. CrossRefADSGoogle Scholar
- Wilson, R.M., Hildner, E.: 1984, Solar Phys. 91, 169. CrossRefADSGoogle Scholar
- Yashiro, S., Gopalswamy, N., Akiyama, S., Michalek, G., Howard, R.A.: 2005, J. Geophys. Res. 110, A12S05. CrossRefGoogle Scholar
- Yashiro, S., Gopalswamy, N., Akiyama, S., Howard, R.A.: 2006, In: 36th COSPAR Scientific Assembly, Beijing, China, 1778. Google Scholar
- Yun-Chun, J., Le-Ping, L., Li-Heng, Y.: 2006, Chin. J. Astron. Astrophys. 6, 345. CrossRefADSGoogle Scholar