Next-Day Prediction of Sunspots Area and McIntosh Classifications Using Hidden Markov Models

Author

Al-Omari, M. ; Qahwaji, R. ; Colak, T. ; Ipson, S. ; Balch, C.

Author_Institution

Sch. of Comput., Inf. & Media, Univ. of Bradford Bradford, Bradford, UK

fYear

2009

Firstpage

253

Lastpage

256

Abstract

In this paper, Hidden Markov Models (HMMs) are used to study the evolution of sunspots and to develop a model that can be used to predict the McIntosh class and the sunspot area for the sunspot under investigation for the next 24 hours. The testing results show accuracy in the prediction of next-day area and McIntosh classification reaching up to 71% and 60% respectively, when studied on the period from 18/08/1996 till 31/03/2006.

Keywords

Markov processes; astronomy computing; solar evolution; sunspots; Automated Solar Activity Prediction system; Hidden Markov Models; McIntosh classification; computer platform; data fusion techniques; sunspot area prediction; sunspots evolution patterns; Earth; Electromagnetic radiation; Hidden Markov models; Humans; Image analysis; Predictive models; Radio communication; Space exploration; Space technology; Weather forecasting; Hidden Markov Models (HMMs); McIntosh Classification; Real-Time Prediction; Space Weather; Sunspot Regions;

fLanguage

English

Publisher

ieee

Conference_Titel

CyberWorlds, 2009. CW '09. International Conference on

Conference_Location

Bradford

Print_ISBN

978-1-4244-4864-7

Electronic_ISBN

978-0-7695-3791-7

Type

conf

DOI

10.1109/CW.2009.10

Filename

5279578