Abstract
We propose an adaptive data-driven approach to modelling solar magnetic activity cyclesbased on a sequential link between unsupervised and supervised modelling. Monthly sunspot numbers spanning over hundreds of years – from the mid-18th century to the first quarter of 2012 - obtained from the Royal Greenwich Observatory provide a reliable source of training and validation sets.An indicator variable is used to generate class labels and internal parameters which are used to separate high from low activity cycles. Our results show that by maximising data-dependent parameters and using them as inputs to a support vector machine model we obtain comparatively more robust and reliable predictions. Finally, we demonstrate how the method can be adapted to other unsupervised and supervised modelling applications.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Clilverd, M., Clarke, E., Ulich, T., Rishbeth, H., Jarvis, M.: Predicting Solar Cycle 24 and beyond. Space Weather 4(7) (2006)
Colak, T., Qahwaji, R.: Automated Solar Activity Prediction: A hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares. Space Weather 7(12) (2009)
Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)
Dempster, A., Laird, N., Rubin, D.: Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society 39, 1–38 (1977)
Glasby, F.: Planets, Sunspots and Earthquakes: Effects on the sun, the earth and its inhabitants; iUniverse (2002) ISBN-13: 978-0595226412
Izenman, A., Wolf, J.R., Wolfer, A.: An Historical Note on the Zurich Sunspot Relative Numbers. Journal of the Royal Statistical Society 146, Part 3, 311–318 (1983)
Kitiashvili, I., Kosovichev, A.: Prediction of solar magnetic cycles by a dataassimilation method; Cosmic Magnetic Fields: From Planets, to Stars and Galaxies. In: Strassmeier, K., Kosovichev, A., Beckman, J. (eds.) Proceedings IAU Symposium, vol. 259. International Astronomical Union (2009)
McLachlan, G., Krishnan, T.: The EM Algorithm and Extensions. John Wiley (1996)
McLachlan, G., Peel, D.: Finite Mixture Models. John Wiley (2000)
Mwitondi, K., Bugrien, J.: Harnessing data flow potentials for sustainable applications of Science, Technology and Innovation for African Development. In: 22nd International CODATA Conference on Scientific Data and Sustainable Development, Cape Town, pp. 24–27 (2010)
Mwitondi, K., Said, R.: A step-wise method for labelling continuous data with a focus on striking a balance between predictive accuracy and model reliability. In: International Conference on the Challenges in Statistics and Operations Research, Kuwait City, March 08-10 (2011)
NOOA (2012), http://www.ngdc.noaa.gov/stp/solar/ssndata.html#hemi
R Version 2.13.0 for Windows; R Foundation for Statistical Computing (2011)
Ross, J.: (2009), http://www.sott.net/articles/show/181839
Silbergleit, V.: Probable Values of Current Solar Cycle Peak. Advances in Astronomy 2012, Article ID 167375 (2012)
Tax, D., Duin, R.: Support Vector Data Description. Machine Learning 54, 45–66 (2004)
Wolf, J.R.: Message from the observatory in Berne. Flacken solar observing. Communications of Natural History; Society in Bern, 169–173 (1848)
Wolf, J.R.: New studies of the period of Sunspots and their meanings. Communications of Natural History; Society in Bern 255, 249–270 (1852)
Wolf, J.R.: Communications on the sunspots. Quarterly Journal of the Entomological Society of Zurich, 157–198 (1861)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mwitondi, K.S., Said, R.T., Yousif, A.E. (2012). A Sequential Data Mining Method for Modelling Solar Magnetic Cycles. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34475-6_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-34475-6_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34474-9
Online ISBN: 978-3-642-34475-6
eBook Packages: Computer ScienceComputer Science (R0)