Statistical Assessment of Photospheric Magnetic Features in Imminent Solar Flares Predictions Hui Song (hxs6800@njit.edu), Vasyl Yurchyshyn , Ju Jing, Changyi Tan , V. I. Abramenko and Haimin Wang Center for Solar-Terrestrial Research, New Jersey Institute of Technology, Newark, NJ 07102 U.S.A Big Bear Solar Observatory, 40386 North Shore Lane, Big Bear City, CA 92314 U.S.A. Abstract. In this study we used the ordinal logistic regression method to establish a prediction model, which estimates the probability for each solar active region to produce X-, M- or C-class flares during the next 1-day time period. Three predictive parameters are: (1) total unsigned magnetic flux T flux , which is a measure of an active region’s size, (2) the length of strong- gradient neutral line L gnl , which describes the global non-potentiality of an active region, and (3) total magnetic dissipation E diss , which is another proxy measure of an active region’s non-potentiality. They are all derived from SOHO MDI magnetograms. The ordinal response variable is the different level of solar flares magnitude. By analyzing 230 active regions, L gnl is proved to be the most powerful predictor, if only one predictor is chosen. Compared with the current predictions methods used by Solar Mornitor at Solar Data Analysis Center (SDAC) and NOAA Space Environment Center (SEC), the ordinal logistic model using L gnl and T flux as predictors demonstrated its automaticity, simpleness and fairly high prediction accuracy. To our knowledge, this is the first time the ordinal logistic regression model was used in solar physics to predict solar flares. 1. Introduction Over the past decades, mankind has become more and more dependent on space systems, satellite-based services, as well as various ground-based facilities. All these technologies are influenced by Sun-Earth interaction phenomena. Therefore, one of the primary objectives in space weather research is to predict the occurrence of solar flares and Coronal Mass Ejections (CMEs), which are believed to be the major causes of geomagnetic disturbances (e.g., Brueckner et al., 1998; Cane et al., 2000; Gopalswamy et al., 2000; Webb et al., 2000; Wang, et al., 2002; Zhang, et al., 2003). It has long been known that solar flares tend to occur along magnetic polarity inversion lines where the magnetic field lines are often highly sheared, with the transverse field directed nearly parallel to the polarity inversion line (Svestka 1976; Hagyard et al. 1984; Sawyer et al. 1986). Canfield et al. (1999) showed that CMEs also tend to arise in connection with active regions (ARs) exhibiting strong sheared and/or twisted coronal loops called sigmoid. The twisting, tangling and shearing of magnetic loops lead c  2007 Kluwer Academic Publishers. Printed in the Netherlands. ms.tex; 26/03/2007; 15:04; p.1