SH022
Prediction of Solar Transient Events using Machine Learning

Session ID#: 159501

Session Description:
Reliable prediction of solar transient events (flares, coronal mass ejections, energetic particle events, etc.) is an important problem from both research and operational perspectives. Over the previous decade, there has been an exponentially-increasing number of attempts to apply machine learning-driven (ML-driven) approaches to forecast such events, induced by the growing amounts of high-quality observational data and accessibility of ML techniques. This session aims to highlight the advances in ML-driven attempts for solar transient event forecasting, the challenges associated with them, and the fundamental physical knowledge derived by them. We welcome all contributions that focus on but are not limited to 1) application of novel ML algorithms and approaches, 2) data preparation and augmentation, 3) forecast assessment/evaluation, 4) class-imbalance treatment strategies, 5) forecast interpretation, and 6) forecast operationalization.
Index Terms:

7513 Coronal mass ejections [SOLAR PHYSICS, ASTROPHYSICS, AND ASTRONOMY]
7514 Energetic particles [SOLAR PHYSICS, ASTROPHYSICS, AND ASTRONOMY]
7519 Flares [SOLAR PHYSICS, ASTROPHYSICS, AND ASTRONOMY]
7924 Forecasting [SPACE WEATHER]

Primary Convener:  Viacheslav M Sadykov, Georgia State University, Atlanta, GA, United States
Conveners:  Dustin Kempton1, Sumanth Rotti2 and Azim Ahmadzadeh1, (1)Georgia State University, Atlanta, GA, United States(2)Georgia State University, Physics and Astronomy, Atlanta, GA, United States
Student/Early Career Convener:  Sumanth Rotti, Georgia State University, Physics and Astronomy, Atlanta, GA, United States
 
Create An Advanced Solar Active Region Database and Predict Solar Flares Using Machine Learning Tools (1049266)
Haimin Wang1, Haodi Jiang2, Yasser Abduallah2 and Jason T. L. Wang2, (1)New Jersey Institute of Technology, Center for Solar-Terrestrial Research, Newark, United States, (2)Institute for Space Weather Sciences, New Jersey Institute of Technology, Newark, United States
 
A DEFT Way to Forecast Solar Flares (Invited) (1092900)
Larisza D Krista, University of Colorado at Boulder, Cooperative Institute for Research in Environmental Sciences (CIRES), Boulder, United States and Matthew Chih, Marietta College, Physics, Worthington, OH, United States
 
Physics, Forecaster, Machine: The Race For Successful Space Weather Forecasts (Invited) (1097829)
Hazel M Bain, CIRES University of Colorado, Boulder, Boulder, CO, United States
 
Feature Vectors and Hybrid Machine Learning Architectures for Solar Flare Prediction using Magnetogram Data (1111264)
Thomas E Berger, University of Colorado, Space Weather Technology, Research, and Education Center, Boulder, United States, Varad Deshmukh, University of Colorado Boulder, Computer Science, Boulder, United States, Natasha Flyer, Flyer Research LLC, Boulder, United States, Elizabeth Bradley, University of Colorado at Boulder, Computer Science, Boulder, CO, United States, James D Meiss, University of Colorado Boulder, Applied Mathematics, Boulder, United States and Kiera van der Sande, University of Colorado at Boulder, Applied Mathematics, Boulder, United States
 
Exploring Performance Trends of Simulated Real-time Solar Flare Predictions (1148424)
Griffin Goodwin1, Viacheslav M Sadykov2 and Petrus C Martens2, (1)Georgia State University, Physics and Astronomy, Atlanta, United States, (2)Georgia State University, Physics and Astronomy, Atlanta, GA, United States
 
Understanding Predictability of Solar Proton Events from GOES statistical features and MHD coronal models. (1150260)
Aatiya Ali, Georgia State University, Atlanta, GA, United States, Viacheslav M Sadykov, Georgia State University, Physics and Astronomy, Atlanta, GA, United States, Alin Paraschiv, High Altitude Observatory, National Center for Atmospheric Research, Boulder, United States, Sarah E Gibson, National Center for Atmospheric Research, High Altitude Observatory, Boulder, CO, United States and Alexander G Kosovichev, New Jersey Institute of Technology, Physics, Newark, NJ, United States
 
An ESPERTA-based Machine Learning forecast tool for Solar Proton Events (1153512)
Mirko Stumpo1, Simone Benella1, Monica Laurenza1, Tommaso Alberti2, Giuseppe Consolini1 and Maria Federica Marcucci1, (1)IAPS-INAF, Rome, Italy, (2)INAF-IAPS, Istituto di Astroļ¬sica e Planetologia Spaziali, Rome, Italy
 
Self-Attention Networks for Short-Term Solar Flare Forecasting Using SDO/AIA Image Data (1186064)
Kiera van der Sande, University of Colorado at Boulder, Applied Mathematics, Boulder, United States, Natasha Flyer, Flyer Research LLC, Boulder, United States, Allison Liu, University of Colorado at Boulder, Department of Applied Mathematics, Boulder, United States and Thomas E Berger, University of Colorado at Boulder, Space Weather Technology, Research, and Education Center, Boulder, United States
 
A real-time solar flare alert system for early flare physics studies: Exploratory data analysis (1189745)
Juan Camilo Buitrago-Casas1, Juliana Therese Vievering2, Subramania Athiray Panchapakesan3, Phillip C Chamberlin4, Lindsay Glesener5, Sam Krucker6, Janet L Machol7, Courtney L Peck7, Marianne S Peterson8, Katharine Reeves9, Sabrina L Savage10, Brent Smith11 and Amy R Winebarger12, (1)University of California Berkeley, Berkeley, CA, United States, (2)Applied Physics Laboratory Johns Hopkins, Laurel, MD, United States, (3)University of Alabama, Huntsville, United States, (4)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (5)University of Minnesota Twin Cities, Minneapolis, United States, (6)UC Berkeley, Space Science Lab, Berkeley, United States, (7)NOAA National Centers for Environmental Information, Boulder, United States, (8)St. Olaf College, Physics, Northfield, United States, (9)Smithsonian Institution, Cambridge, United States, (10)NASA Marshall Space Flight Center, Huntsville, United States, (11)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (12)NASA Marshall Space Flight Center, Huntsville, AL, United States
 
Practices for Using Data-Centric Machine Learning with Imbalanced Classes: A Case of SPE Occurrence Prediction (1190614)
Patrick O'Keefe1, Viacheslav M Sadykov2, Alexander G Kosovichev3, Gelu M Nita4, Vincent Oria5, Shantanu Sharma1, Fraila Francis1 and Chun Jie Chong1, (1)New Jersey Institute of Technology, Newark, United States, (2)Georgia State University, Atlanta, GA, United States, (3)New Jersey Institute of Technology, Physics, Newark, NJ, United States, (4)New Jersey Institute of Technology, Center for Solar-Terrestrial Research, Edison, NJ, United States, (5)New Jersey Institute of Technology, Computer Science, Newark, NJ, United States
 
Steps to Generating an SDO/AIA based Flare Catalog (1197748)
Kiera van der Sande, University of Colorado at Boulder, Applied Mathematics, Boulder, United States, Natasha Flyer, Flyer Research LLC, Boulder, United States and Thomas E Berger, University of Colorado at Boulder, Space Weather Technology, Research, and Education Center, Boulder, United States
See more of: SPA-Solar and Heliospheric Physics
<< Previous Session Proposal | Next Session Proposal >>