Authors: Aatiya Ali (Georgia State University), Viacheslav Sadykov (Georgia State University), Alexander Kosovichev (New Jersey Institute of Technology), Alin Paraschiv (High Altitude Observatory), Sarah Gibson (High Altitude Observatory)

Solar energetic particles (SEPs) and their propagation through the heliosphere and interactions with Earth’s atmosphere result in unfavorable consequences to numerous aspects of life and technology. Enhancements of energetic proton fluxes from the Sun observed near Earth, otherwise known as Solar proton events (SPEs) are infrequent, with less than 50 events detected during solar cycle 24. Therefore, to robustly predict SPEs, it becomes crucial to evaluate prediction models based on data from multiple solar cycles. In this work, we report the completion of a catalog of ⩾ 10 MeV ⩾ 10 pfu SPEs observed by GOES with records of their properties (start and end times, peak flux, fluence, etc.) spanning through solar cycles 22-24. A catalog of daily proton and soft X-ray fluxes’ statistical properties is also constructed to serve as input data when applying different machine-learning methods to forecast SPEs. We emphasize the effects of training our model on single or paired cycles and assess changes in forecast applicability. We also discuss future work using SolarSoft’s FORWARD suite for coronal model-data comparison using CoMP & uCoMP observations. By considering coronal magnetohydrodynamic models, we will investigate plasma conditions of regions spawning coronal mass ejections and their relevance toward SPE production.