Solar Energetic Particles (SEPs) are among the most hazardous transient phenomena of the solar activity. Accelerated during solar flares or in shock wave fronts of coronal mass ejections (CMEs), SEPs propagate through the heliosphere and interact with the space environment. Representing hazardous radiation, SEPs may affect health of astronauts in the open space and create difficulties for the future space exploration. We are currently living in the era of big observational and modeling data and advanced computational capabilities, and should use these advantages for improving operational forecasts of SEPs. The SEP Prediction Portal (SEP3) project developed within the NASA's Early Stage Innovation (ESI) project will enable the development of targeted applications of modern machine learning and data analysis techniques to enhance reliability of the SEP forecasts.
The primary objective of the proposed research is to enhance predictions of solar energetic particles (SEP) by implementing automatic data characterization and machine-learning tools. The proposal pursuits two main goals: 1) development of an online-accessible automatically-updated database that integrates the solar and heliospheric data, metadata, and descriptors related to SPEs; 2) development of robust "all-clear" forecasts of SPEs with low false-alarm rates, targeted at different temporal scales (cadences and lead times), different energy and particle flux thresholds of SPEs, and adapted to operational availability of data sources and gaps in the data. Using the available resources and previously developed tools and methodologies, the proposal team will achieve a transformative change from the current low Technology Readiness Level (TRL) to high-TRL in these tasks.
We thank SDO/HMI and GOES satellite teams for providing the high-quality scientific data and related data products. We thank Space Weather Prediction Center at National Oceanic and Atmospheric Administration (SWPC NOAA) for providing operational reports and predictions of space weather events. The Bootstrap API is distributed under MIT license. This work is supported by NASA ESI grant 80NSSC20K0302 and NSF grants 1916509 and 1639683.