An ensemble prediction model of solar proton events （SPEs）, combining the information of solar flares and coronal mass ejections （CMEs）, is built. In this model, solar flares are parameterized by the peak flux, the duration and the longitude. In addition, CMEs are parameterized by the width, the speed and the measurement position angle. The importance of each parameter for the occurrence of SPEs is estimated by the information gain ratio. We find that the CME width and speed are more informative than the flare’s peak flux and duration. As the physical mechanism of SPEs is not very clear, a hidden naive Bayes approach, which is a probability-based calculation method from the field of machine learning, is used to build the prediction model from the observational data. As is known, SPEs originate from solar flares and/or shock waves associated with CMEs. Hence, we first build two base prediction models using the properties of solar flares and CMEs, respectively. Then the outputs of these models are combined to generate the ensemble prediction model of SPEs. The ensemble prediction model incorporating the complementary information of solar flares and CMEs achieves better performance than each base prediction model taken separately.
With the observations of the Solar-Terrestrial Relations Observatory （STEREO） and the Solar Dynamics Observatory （SDO）, we analyze in detail the kine- matics of global coronal waves together with their intensity amplitudes （so-called ＂perturbation profiles＂）. We use a semi-automatic method to investigate the pertur- bation profiles of coronal waves. The location and amplitude of the coronal waves are calculated over a 30~ sector on the sphere, where the wave signal is strongest. The position with the strongest perturbation at each time is considered as the location of the wave front. In all four events, the wave velocities vary with time for most of their lifetime, up to 15 rain, while in the event observed by the Atmospheric Imaging Assembly there is at, additional early phase with a much higher velocity. The velocity varies greatly between different waves from 216 to 440 km s-1. The velocity of the two waves initially increases, subsequently decreases, and then increases again. Two other waves show a deceleration followed by an acceleration. Three categories of am- plitude evolution of global coronal waves are found for the four events. The first is that the amplitude only shows a decrease. The second is that the amplitude initially increases and then decreases, and the third is that the amplitude shows an orderly in- crease, a decrease, an increase again and then a decrease. All the extreme ultraviolet waves show a decrease in amplitude while propagating farther away, probably because the driver of the global coronal wave （coronal mass ejection） is moving farther away from the solar surface.
