Solar energetic particles (SEPs) endanger satellites and astronauts in orbit and can disrupt air traffic and spaceflight communication, among other effects. Therefore, the ability to forecast these events in advance is vital, both, economically, and for the safety of air and space-faring passenge... Show moreSolar energetic particles (SEPs) endanger satellites and astronauts in orbit and can disrupt air traffic and spaceflight communication, among other effects. Therefore, the ability to forecast these events in advance is vital, both, economically, and for the safety of air and space-faring passengers. Considering that the method of acceleration and transport of these particles is still an area of active research and that physics-based models are, currently, computationally slower than empirical models, forecasters at NOAA's Space Weather Prediction Center make use of the latter to make real-time decisions. The motivation behind this project was to create a model that improves upon the results of the statistical model currently in use at the Space Weather Prediction Center. Machine learning models learn and make decisions based on empirical data and are currently much quicker than numerical models for issuing a forecast. For this project, logistic regression and boosted decision trees are used to make a binary classification, i.e. whether or not there will be an SEP event based on the physical parameters associated with solar flares and coronal mass ejections. Preliminary results seem to show that the boosted decision trees outperform the current SWPC Proton Prediction Model. Show less
