Abstracts submitted by Tufan Colak
Hybrid Computer Platform for the Automated Prediction of Solar Flares
T. Colak and R. Qahwaji
University of Bradford
The importance of real-time processing of solar data especially for space weather applications is increasing continuously. In this work, we will be presenting our real-time automated model for the short-term prediction of significant solar flares using SOHO/MDI images. This model integrates image processing and machine learning to deliver these predictions. A machine learning-based system is designed to study years of sunspots and flares data to extract knowledge and create associations that can be represented using learning rules, which can be applied using computers. An imaging-based real time system that provides automated detection, grouping and then classification of recent sunspots based on the McIntosh classification is also created and integrated within this system. The automated classifications created by the imaging system are processed using the learning rules to create real-time predictions. This system is currently under testing and is publicly available at http://spaceweather.inf.brad.ac.uk/. |
|
|