Probabilistic Forecast of Solar Energetic Particle (SEP) Events
- Paper number
IAC-23,D5,3,6,x80650
- Author
Dr. Maher Dayeh, Southwest Research Institute, United States
- Coauthor
Dr. Subhamoy Chatterjee, Southwest Research Institute, United States
- Coauthor
Dr. Andres Munoz-Jaramillo, Southwest Research Institute, United States
- Coauthor
Mrs. Kimberly Moreland, University of Texas at San Antonio, United States
- Coauthor
Dr. Hazel Bain, National Oceanic and Atmospheric Administration (NOAA), United States
- Coauthor
Mr. Samuel Hart, University of Texas at San Antonio, United States
- Year
2023
- Abstract
Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather. While some CMEs and flares are associated with intense SEPs, some show no or little SEP association in the near-Earth environment. The latter is due to the complexities that dominate SEP origin, acceleration, and transport. To date, robust long-term (hours to days) forecasting of SEPs does not effectively exist. We present an ensemble of neural networks that uses a comprehensive dataset from multiple sources to predict the true probability of SEP occurrence and its properties (e.g., peak intensity, onset time, and duration). We show that incorporating the SEP occurrence probability as a weighting factor into the regression can tighten the prediction of event properties on the test set. We also show how the uncertainty estimated through the ensemble of models enables robust forecasting decisions for unseen data.
- Abstract document
- Manuscript document
IAC-23,D5,3,6,x80650.pdf (🔒 authorized access only).
To get the manuscript, please contact IAF Secretariat.