SPRINTS - Space Radiation Intelligence System

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 (HSS) are critical in assessing their... [ view full abstract ]

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 (HSS) are critical in assessing their potential impacts. We introduce the Space Radiation Intelligence System (SPRINTS), a NASA invested technology, that combines pre-eruptive metadata and forecasts from the MAG4 system with post-eruptive metadata to enable high fidelity and pre-to-post transitional solar-driven event forecasts.  Automatic detections are employed on 30+ years of GOES X-ray and particle data and 20+ years of ACE/DSCOVR solar wind data to determine start and end times of the four solar-driven events and create their respective catalogs.  The focus and results presented here is SPRINTS post-eruptive capability for forecasting SEPs.  We present onset, magnitude, and time-profile forecast metrics and results based on expert-guided, statistical, and machine-learned decision tree models.  For a 20 year period, a machine learned decision tree model proved to the be the best for predicting 10 MeV events achieving 10 pfu; 86% probability of detection and a 38% false alarm rate. Five flare related metadata sets were leveraged in the decision-tree modeling.  Consistently, flare integrated flux, flare heliolongitude, and flare decay phase duration are found to be the top three forecasting parameters, while flare magnitude had negligible to no impact on the SEP forecast model.  We demonstrate SPRINTS abilities to forecast onset and time-profiles of the October 1989, October 2003, and March 2012 events in operational tools.