Forecasting sunspot numbers with the aid of fuzzy descriptor models

The cyclic solar activity has significant effects on Earth, satellites, and space missions. The prediction of sunspot number is an active research area and several methods have been introduced for its prediction, which is a common measure of solar activity. On the other hand, descriptor models and r...

Full description

Saved in:
Bibliographic Details
Published in:Space weather Vol. 5; no. 8; pp. np - n/a
Main Authors: Mirmomeni, Masoud, Lucas, Caro, Araabi, Babak Nadjar, Shafiee, Masoud
Format: Journal Article
Language:English
Published: Blackwell Publishing Ltd 01.08.2007
Subjects:
Chaotic dynamics
fuzzy descriptor models
GLOLIMOT
neurofuzzy models
solar activity
sunspot number
ISSN:1542-7390, 1542-7390
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The cyclic solar activity has significant effects on Earth, satellites, and space missions. The prediction of sunspot number is an active research area and several methods have been introduced for its prediction, which is a common measure of solar activity. On the other hand, descriptor models and related fuzzy descriptor models have been the subjects of interest due to their many practical applications in modeling complex phenomena. In this study, it is tried to predict sun spot number by a data driven approach. In other words, instead of other methods which are based on sophisticated models, in this paper a fuzzy descriptor model is used as a black box to predict sunspot number. To do so, a novel learning method, generalized locally linear model tree (GLOLIMOT) algorithm for fuzzy descriptor models as an intuitive incremental learning algorithms, is introduced to tune the parameters of fuzzy descriptor model for the prediction of sunspot number via empirical data. The contribution of this paper is to provide some methods for adjusting the parameters of fuzzy descriptor model, e.g., the splitting ratio and the standard deviation, the number of locally linear neurons and the number of linear descriptor systems for the consequent part in fuzzy descriptor model and especially the parameters of such descriptor systems which need some special methods for these systems. By these modifications an accurate prediction of sunspot number is obtained which, when compared with several methods and results, depict the power of these systems in predicting such complex phenomena.
Bibliography:ark:/67375/WNG-07LM3941-3
istex:EA3DE097A98151277D77EE5DA740E072EDB86E32
Tab-delimited Table 1.
ArticleID:2006SW000289
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1542-7390
1542-7390
DOI:10.1029/2006SW000289