Enhancements in the Prediction of Solar Activity by Locally Linear Model Tree

A. Gholipour, A. Abbaspour, B.N. Araabi, and C. Lucas (Iran)


Prediction, Solar activity, Sunspot Number, Neuro fuzzy Model, Locally Linear Model, LOLIMOT.


The cyclic solar activity has significant effects on earth, climate, satellites and space missions. Several methods have been introduced for the prediction of sunspot number, which is a common measure of solar activity. In this research, a relatively new neurofuzzy method, the locally linear model tree (LOLIMOT), has been used in the prediction of sunspot number. This method is characterized by high generalization and in this way it is appropriate for prediction. The contribution of this paper is to provide some methods for adjusting the parameters of LOLIMOT, e.g. the splitting ratio and standard deviations, the number of locally linear neurons and the number of regressors. By these modifications an accurate prediction of sunspot number is obtained which is compared with several other methods.

Important Links:

Go Back