On Learning of Sunspot Classification

This paper describes automatic sunspot recognition and classification from satellite images. Some experimental results on learning sunspot classification using data mining techniques are presented. The classification scheme attempted was the seven-class Modified Zurich scheme. Daily images of the solar disk were taken from the NASA SOHO satellite’s MDI instrument and sunspots extracted using image processing techniques. Two data mining tools, WEKA and RSES, were used for learning sunspot classification. In the training dataset sunspots were manually classified by comparing extracted sunspots with corresponding active region maps (ARMaps) from the Mees Observatory at the Institute for Astronomy, University of Hawaii.