ASAP: A Hybrid Computer Platform Using Machine

7 The importance of real-time processing of solar data especially for space weather 8 applications is increasing continuously. In this paper, we present an automated hybrid 9 computer platform for the short-term prediction of significant solar flares using SOHO/MDI 10 images. This platform is called the Automated Solar Activity Prediction tool, or simply 11 ASAP. This system integrates image processing and machine learning to deliver these 12 predictions. A machine learning-based system is designed to analyze years of sunspot and 13 flare data to create associations that can be represented using computer-based learning rules. 14 An imaging-based real time system that provides automated detection, grouping and then 15 classification of recent sunspots based on the McIntosh classification is also created and 16 integrated within this system. The properties of the sunspot regions are extracted 17 automatically by the imaging system and processed using the machine learning rules to 18 generate the real-time predictions. Several performance measurement criteria are used and the 19 results are provided in this paper. Also, Quadratic Score (QR) is used to compare the 20 prediction results of ASAP with NOAA Space Weather Prediction Center (SWPC) between 21 1999 and 2002, and it is shown that ASAP generates more accurate predictions compared to 22 SWPC. 23