Monday, 8 January 2018
Exhibit Hall 3 (ACC) (Austin, Texas)
Capabilities to predict onset and time-profiles of solar-driven events, including solar X-ray flares; solar energetic particles (SEP); coronal mass ejections (CME); and high-speed streams, are critical in mitigating their potential impacts. We introduce the Space Radiation Intelligence System (SPRINTS), a NASA invested technology, that integrates pre-eruptive metadata and forecasts from the MAG4 system with post-eruptive metadata to enable high fidelity and pre-to-post eruptive transitional solar-driven event forecasts. SPRINTS is capable of generating post-eruptive forecasts based on automatic detections employed on 30+ years of GOES X-ray and particle data and 20+ years of ACE and DSCOVR solar wind data to catalog start and end times of the four solar-driven events. The prediction results for 1986-2016 presented here are from the SPRINTS post-eruptive capability for forecasting SEPs leveraging GOES X-ray metadata. We present onset, peak flux, and time-profile SEP forecast metrics and results based on expert-guided, statistical, and machine-learned decision tree models. Operating on data from a 20-year period, a machine-learned decision tree model provided the best results for predicting an S1 event (on the NOAA SWPC Solar Radiation Scale): 86% probability of detection (POD) and 37% false alarm rate (FAR). Five flare-related metadata sets were leveraged in the decision-tree modeling. Consistently, flare integrated flux, flare heliolongitude, and flare decay phase duration were found to be the top three forecasting parameters, while flare magnitude and flare latitude had little to no impact on the SEP forecast model. For the solar-driven events of March 2012, we demonstrate SPRINTS abilities to forecast solar flares, SEP onset, and SEP evolution.
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner