Evaluation of the UMASEP-10 Version 2 Tool for Predicting All >10 MeV SEP Events of Solar Cycles 22, 23 and 24

: The prediction of solar energetic particle (SEP) events may help to improve the mitigation of adverse effects on humans and technology in space. UMASEP (University of M á laga Solar particle Event Predictor) is an empirical model scheme that predicts SEP events. This scheme is based on a dual-model approach. The first model predicts well-connected events by using an improved lag-correlation algorithm for analyzing soft X-ray (SXR) and differential proton fluxes to estimate empirically the Sun–Earth magnetic connectivity. The second model predicts poorly connected events by analyzing the evolution of differential proton fluxes. This study presents the evaluation of UMASEP-10 version 2, a tool based on the aforementioned scheme for predicting all >10 MeV SEP events, including those without associated flare. The evaluation of this tool is presented in terms of the probability of detection (POD), false alarm ratio (FAR) and average warning time (AWT). The best performance was achieved for the solar cycle 24 (i.e., 2008–2019), obtaining a POD of 91.1% (41/45), a FAR of 12.8% (6/47) and an AWT of 2 h 46 min. These results show that UMASEP-10 version 2 obtains a high POD and low FAR mainly because it is able to detect true Sun–Earth magnetic connections.

[1]  T. Onsager,et al.  A Summary of National Oceanic and Atmospheric Administration Space Weather Prediction Center Proton Event Forecast Performance and Skill , 2021, Space Weather.

[2]  I. Daglis,et al.  Assessing the Predictability of Solar Energetic Particles with the Use of Machine Learning Techniques , 2021, Solar Physics.

[3]  G. Consolini,et al.  Open Issues in Statistical Forecasting of Solar Proton Events: A Machine Learning Perspective , 2021, Space Weather.

[4]  Marlon Núñez,et al.  Predicting >10 MeV SEP Events from Solar Flare and Radio Burst Data , 2020, Universe.

[5]  Marlon Núñez,et al.  Predicting well-connected SEP events from observations of solar EUVs and energetic protons , 2019, Journal of Space Weather and Space Climate.

[6]  Marlon Núñez.  Predicting well-connected SEP events from observations of solar soft X-rays and near-relativistic electrons , 2018 .

[7]  Anastasios Anastasiadis,et al.  Nowcasting Solar Energetic Particle Events Using Principal Component Analysis , 2018, Solar Physics.

[8]  A. Papaioannou,et al.  Nowcasting of Solar Energetic Particle Events using near real-time Coronal Mass Ejection characteristics in the framework of the FORSPEF tool , 2018 .

[9]  S. Samwel,et al.  The Wind/EPACT Proton Event Catalog (1996 – 2016) , 2018, 1801.00469.

[10]  Marlon Núñez,et al.  HESPERIA Forecasting Tools: Real-Time and Post-Event , 2018 .

[11]  Soukaina Filali Boubrahimi,et al.  On the prediction of >100 MeV solar energetic particle events using GOES satellite data , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[12]  M. L. Mays,et al.  Modeling solar energetic particle events using ENLIL heliosphere simulations , 2017 .

[13]  Marlon Núñez,et al.  Real‐time prediction of the occurrence of GLE events , 2017 .

[14]  Marlon Núñez,et al.  Exploring the potential of microwave diagnostics in SEP forecasting: The occurrence of SEP events , 2017 .

[15]  G. Consolini,et al.  Solar Activity from 2006 to 2014 and Short-term Forecasts of Solar Proton Events Using the ESPERTA Model , 2017 .

[16]  A. Posner,et al.  Solar energetic particle warnings from a coronagraph , 2017 .

[17]  Manolis K. Georgoulis,et al.  Solar flares, coronal mass ejections and solar energetic particle event characteristics , 2016 .

[18]  Teresa Nieves-Chinchilla,et al.  Prediction of shock arrival times from CME and flare data , 2016, Space weather : the international journal of research & applications.

[19]  M. Hernández‐Pajares,et al.  Prediction and warning system of SEP events and solar flares for risk estimation in space launch operations , 2016 .

[20]  Marlon Núñez.  Real‐time prediction of the occurrence and intensity of the first hours of >100 MeV solar energetic proton events , 2015 .

[21]  L. Winter,et al.  TYPE II AND TYPE III RADIO BURSTS AND THEIR CORRELATION WITH SOLAR ENERGETIC PROTON EVENTS , 2015, 1507.01620.

[22]  M. Dierckxsens,et al.  Relationship between Solar Energetic Particles and Properties of Flares and CMEs: Statistical Analysis of Solar Cycle 23 Events , 2014, Solar Physics.

[23]  M. Dierckxsens,et al.  SPARX: A modeling system for Solar Energetic Particle Radiation Space Weather forecasting , 2014, 1409.6368.

[24]  Rami Qahwaji,et al.  Progress in space weather modeling in an operational environment , 2013 .

[25]  M. Shea,et al.  Space Weather and the Ground-Level Solar Proton Events of the 23rd Solar Cycle , 2012 .

[26]  Raul Fidalgo-Merino,et al.  Self-Adaptive Induction of Regression Trees , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Marlon Núñez,et al.  Predicting solar energetic proton events (E > 10 MeV) , 2011 .

[28]  M. L. Kaiser,et al.  A technique for short‐term warning of solar energetic particle events based on flare location, flare size, and evidence of particle escape , 2009 .

[29]  D. Lario,et al.  Comparing proton fluxes of central meridian SEP events with those predicted by SOLPENCO , 2008 .

[30]  Christopher C. Balch,et al.  Updated verification of the Space Weather Prediction Center's solar energetic particle prediction model , 2008 .

[31]  A. Posner,et al.  Up to 1‐hour forecasting of radiation hazards from solar energetic ion events with relativistic electrons , 2007 .

[32]  David Lario,et al.  SOLPENCO: A solar particle engineering code , 2006 .

[33]  P. Beck,et al.  TEPC reference measurements at aircraft altitudes during a solar storm , 2005 .

[34]  S. Solomon,et al.  Coupled model simulation of a Sun-to-Earth space weather event , 2004 .

[35]  Donald V. Reames,et al.  Solar energetic particle variations , 2004 .

[36]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[37]  M. Shea,et al.  PPS-87: a new event oriented solar proton prediction model. , 1989, Advances in space research : the official journal of the Committee on Space Research.

[38]  S. W. Kahlera,et al.  Validating the proton prediction system ( PPS ) , 2022 .