Browse > Article
http://dx.doi.org/10.5303/JKAS.2012.45.2.31

APPLICATION OF SUPPORT VECTOR MACHINE TO THE PREDICTION OF GEO-EFFECTIVE HALO CMES  

Choi, Seong-Hwan (Korea Astronomy and Space Science Institute)
Moon, Yong-Jae (Department of Astronomy and Space Science, Kyung Hee University)
Vien, Ngo Anh (Institute for Artificial Intelligence, Ravensburg-Weingarten University of Applied Sciences)
Park, Young-Deuk (Korea Astronomy and Space Science Institute)
Publication Information
Journal of The Korean Astronomical Society / v.45, no.2, 2012 , pp. 31-38 More about this Journal
Abstract
In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.
Keywords
space weather; CME; flare; machine learning; support vector machine;
Citations & Related Records
 (Related Records In Web of Science)
연도 인용수 순위
  • Reference
1 Yuan, Y., Shih, F. Y., Jing, J., &Wang, H. 2010, Auto- mated Flare Forecasting using a Statistical Learning Technique, Res. Astron. Astrophys., 10, 785   DOI   ScienceOn
2 Zhang, J., Richardson, I. G., Webb, D. F., Gopal- swamy, N., Huttunen, E., Kasper, J. C., Nitta, N. V., Poomvises, W., Thompson, B. J., Wu, C.-C., Yashiro, S., & Zhukov, A. N. Solar and Interplane- tary Sources of Major Geomagnetic Storms (Dst ${\leq}$-100 nT) during 1996-2005, JGRA, 112, A10
3 Liu, D. D., Huang, C., Lu, J. Y., & Wang, J. S. 2011, The Hourly Average Solar Wind Velocity Prediction Based on Support Vector Regression Method, MNRAS, 413, 2877   DOI   ScienceOn
4 Qahwaji, R., Colak, T., Al-Omari, M., & Ipson, S. 2008, Automated Prediction of CMEs Using Ma- chine Learning of CME-Flare Associations, Solar Physics, 248, 471   DOI   ScienceOn
5 Martens, P. C. H., Attrill, G. D. R., Davey, A. R., Engell, A., Farid, S., Grigis, P. C., Kasper, J., Kor- reck, K., Saar, S. H., Savcheva, A., Su, Y., Testa, P., Wills-Davey, M., Bernasconi, P. N., Raouafi, N.-E., Delouille, V. A., Hochedez, J. F., Cirtain, J.W., De- forest, C. E., Angryk, R. A., de Moortel, I., Wiegel- mann, T., Georgoulis, M. K., McAteer, R. T. J., & Timmons, R. P. 2009, Computer Vision for the Solar Dynamics Observatory (SDO), Solar Physics, tmp 144
6 Moon, Y.-J., Cho, K.-S., Chae, J., Choe, G. S., Kim, Y.-H., Bong, S.-C., & Park, Y.-D. New Extrapola- tion Method for Coronal Mass Ejection Onset Time Estimation, JGR, 110, A7
7 Qahwaji, R., & Colak, T. 2007, Automated Short- Solar Flare Prediction Using Machine Learning and Sunspot Associations, Solar Physics, 241, 195   DOI   ScienceOn
8 Qu, M., Shih, F. Y., Jing, J., & Wang, H. 2003, Auto- mated Solar Flare Detection Using MLP, RBF, and SVM, Solar Physics, 217, 157   DOI   ScienceOn
9 Qu, M., Shin, F. Y., Jing, J., & Wang, H. 2005, Au- tomatic Solar Filament Detection Using Image Pro- cessing Techniques, Solar Physics, 228, 119   DOI   ScienceOn
10 Srivastava, N. K., & Venkatakrishnan, P. 2004, Solar and Interplanetary Sources of Major Geomagnetic Storms during 1996-2002, JGR, 109, A10
11 Wang, Y.M., Ye, P. Z.,Wang, S., Zhou, G. P., &Wang, J. X. 2002, A Statistical Study on the Geoeffective- ness of Earth-Directed Coronal Mass Ejections from March 1997 to December 2000, JGR, 107, A11
12 Webb, D. F. 2002, CMEs and the Solar Cycle Varia- tion in Their Geoeffectiveness, ISBN 92-9092-818-2, 2002, 409
13 Yu, D., Huang, X., Wang, H., & Cui, Y. 2009, Short- Term Solar Flare Prediction Using a Sequential Supervised Learning Method, Solar Physics, 255, 91   DOI   ScienceOn
14 Gopalswamy, N., Lara, A., Yashiro, S., Kaiser, M. L., & Howard, R. A. Predicting the 1-AU Arrival Times of Coronal Mass Ejections, JGR, 106, A12, 29207
15 Colak, T., & Qahwaji, R. 2009, Automated Solar Ac- tivity Prediction: A Hybrid Computer Platform Us- ing Machine Learning and Solar Imaging for Auto- mated Prediction of Solar Flares, Space Weather, Vol. 7, S06001, 12PP
16 Cortes, C., & Vapnik, V. 1995, Support-Vector Networks, Machine Learning, 20
17 Gavrishchaka, V. V., & Ganguli, S. B. 2001, Support Vector Machine as an Efficient Tool for High-Dimensional Data Processing: Application to Substorm Forecasting, JGR, 106, 29911   DOI
18 Gopalswamy, N., Yashiro, S., & Akiyama, S. Geoeffec- tiveness of Halo Coronal Mass Ejections, JGR, 112, A6
19 He, H., Wang, H., Du, z., Li, R., Chui, Y., Zhang, L., & He, Y. 2008, Solar Activity Prediction Studies and Services in NAOC, Advances in Space Research, 42, 1450   DOI   ScienceOn
20 Henwood, R., Chapman, S. C., & Willis, D. M. 2010, Increasing Lifetime of Recurrent Sunspot Groups Within the Greenwich Photoheliographic Results, Solar Physics, 262, 299   DOI   ScienceOn
21 Kim, R.-S., Cho, K.-S., Moon, Y.-J., Kim, Y.-H., Yi, Y., Dryer, M., Bong, S.-C., & Park, Y.-D. 2005, Forecast Evaluation of the Coronal Mass Ejection (CME), Geoeffectiveness Using Halo CMEs from 1997 to 2003, JGR, 110, A11104   DOI
22 Kim, R.-S., Cho, K.-S., Kim, K.-H., Park, Y.-D., Moon, Y.-J., Yi, Y., Lee, J., Wang, H., Song, H., & Dryer, M. 2008, CME Earthward Direction as an Important Geoeffectiveness Indicator, ApJ, 677, 1378   DOI
23 Labrosse, N., Dalla, S., & Marshall, S. 2010, Auto- mated Detection of Limb Prominences in 304 A EUV Images, Solar Physics, 262, 449   DOI   ScienceOn
24 Li, R., Wang, H.-N., He, H., Cui, Y.-M., & Du, Z.-L. 2007, Support Vector Machine Combined with K- Nearest Neighbors for Solar Flare Forecasting, Chin. J. Astron. Astrophys., Vol. 7, No. 3, 441   DOI   ScienceOn
25 Al-Omari, M., Qahwaji, R., Colak, T., & Ipson, S. 2010, Machine Learning-Based Investigation of the Associations between CMEs and Filaments, Solar Physics, 262, 511   DOI   ScienceOn
26 Attrill, G. D. R., &Wills-Davey, M. J. 2010, Automatic Detection and Extraction of Coronal Dimmings from SDO/AIA Data, Solar Physics, 262, 461   DOI   ScienceOn
27 Boser, B. E., Guyon, I. M., & Vapnik, V. N. 1992, 5th Annual ACM Workshop on COLT, pages 144152, Pittsburgh, PA, A training algorithm for optimal margin classifiers. In D. Haussler, editor, ACM Press
28 Chang, C.-C., & Lin, C.-J. 2001, LIBSVM : A Library for Support Vector Machines, http://www.csie.ntu.edu.tw/ cjlin/libsvm
29 Chen, C., Wu, Z. S., Xu, Z. W., Sun, S. J., Ding, Z. H., & Ban, P. P. 2010, Forecasting the Local Ionospheric f0F2 Parameter 1 Hour ahead during Disturbed Ge- omagnetic Conditions, JGR, 115, A11315   DOI