Date of Award
Master of Science (MS)
Computer Engineering and Sciences
Marius C. Silaghi
Philip J. Bernhard
High intensity Solar Energetic Particle (SEP) events pose severe risks for astronauts and critical infrastructure. The ability to accurately forecast the peak intensity and times of these events would enable preparatory measures to mitigate much of this risk. Machine learning approaches have the potential to use characteristics of CMEs and other space weather phenomena to predict SEP intensities and times. However, the severe sparsity of SEP events in current datasets poses a problem to traditional machine learning techniques. In this work, we present a dataset of proton event intensities and times, as well as features for corresponding CMEs and space weather events. We then demonstrate machine learning techniques for imbalanced data that are able to achieve an MAE of 1.50, a TSS of 0.74, an HSS of 0.73, and an F1-Score of 0.74 for intensity prediction. Additionally, we demonstrate our models’ ability to forecast SEP event times, achieving an MAE of 0.74 for threshold and an MAE of 0.69 for peak times.
Thomas, Peter John, "A Machine Learning Approach to Forecasting SEP Intensity and Times based on CME and other Solar Activities" (2022). Theses and Dissertations. 1281.