SM54A:
Machine Learning in Space Weather II


Submit an Abstract to this Session


Session ID#: 60879

Session Description:
In the last few years, we have witnessed several ground-breaking results in Artificial Intelligence, such as image recognition at super-human accuracy, real-time voice translation, automatic image captioning, and the notorious defeat of a world champion in the game of Go.
Machine Learning is revolutionizing our world, and is rapidly making an impact in science too.The large amount of data at our disposal puts Space Physics in an optimal position to capitalize on the recent progresses. Potentially, every model in the Space Weather chain, from the forecast of solar phenomena to the prediction of geomagnetic disturbances, can be enhanced with a machine-learned approach.

This session will focus on applications of Machine Learning to problems in Space Weather and Heliophysics. Contributions ranging from black-box models to data-driven physics-based simulations are welcome, including (but not limited to) regression and classification problems, dimensionality reduction, automatic event identification, Bayesian inference, feature extraction, deep learning, and reinforcement learning.
Primary Convener:  Enrico Camporeale, Centrum Wiskunde & Informatica, Amsterdam, Netherlands
Conveners:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Pasadena, CA, United States, Thomas E Berger, University of Colorado, Space Weather Technology, Research, and Education Center, Boulder, United States and Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States
Primary Liaison:  Enrico Camporeale, University of Colorado, Queen Mary University of London, Boulder, United States
Chairs:  Enrico Camporeale, University of Colorado, Queen Mary University of London, Boulder, United States and Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States
OSPA Liaison:  Enrico Camporeale, University of Colorado, Queen Mary University of London, Boulder, United States
Co-Organized with:
SPA-Magnetospheric Physics, and SPA-Solar and Heliospheric Physics

Cross-Listed:
  • SA - SPA-Aeronomy
  • SH - SPA-Solar and Heliospheric Physics

Proposed Co-Organized Session with:
  • SA - SPA-Aeronomy
  • SH - SPA-Solar and Heliospheric Physics
Index Terms:

1942 Machine learning [INFORMATICS]
7924 Forecasting [SPACE WEATHER]
7959 Models [SPACE WEATHER]
7999 General or miscellaneous [SPACE WEATHER]

Abstracts Submitted to this Session:

Solar EUV Spectral Irradiance by Deep Learning (427836)
Chun Ming Mark Cheung, Lockheed Martin Solar and Astrophysics Laboratory, Palo Alto, CA, United States, Alexandre Szenicer, University of Oxford, Oxford, United Kingdom, Richard Galvez, New York University, New York, NY, United States, Paul James Wright, University of Glasgow, Glasgow, G12, United Kingdom, David Fouhey, University of California, Berkeley, Berkeley, United States, Meng Jin, SETI Institute, Mountain View, United States, Andrés Muñoz-Jaramillo, Southwest Research Institute, Boulder, United States, Graham Mackintosh, NASA Frontier Development Lab, Mountain View, CA, United States and Rajat Thomas, University of Amsterdam, Amsterdam, Netherlands
Machine Learning and the "Holy Grail" of Space Weather Forecasting (349407)
Tamas I Gombosi1, Yang Chen2, Ward Manchester3, Shasha Zou3, Alfred O Hero4, Enrico Landi5, Gabor Toth3 and Justin Christophe Kasper3, (1)University of Michigan Ann Arbor, Climate and Space Sciences and Engineering, Ann Arbor, MI, United States, (2)University of Michigan, Department of Statistics, Ann Arbor, MI, United States, (3)University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, United States, (4)University of Michigan Ann Arbor, Ann Arbor, United States, (5)University of Michigan, Ann Arbor, MI, United States
Predicting Time Lagged Effects of Solar Disturbances from Heliospheric Images: A Deep Learning Approach (368179)
Mandar Chandorkar1, Enrico Camporeale2, Cyril Furthlener3 and Michélè Sebag3, (1)Centrum Wiskunde & Informatica, Amsterdam, Netherlands, (2)University of Colorado, Queen Mary University of London, Boulder, United States, (3)INRIA Paris-Saclay, Paris, France
Data Assimilation in the Solar Wind (Invited) (390677)
Matthew Lang, LSCE Laboratoire des Sciences du Climat et de l'Environnement, Gif-Sur-Yvette Cedex, France, Mathew James Owens, University of Reading, Reading, United Kingdom, Phil Browne, European Center for Medium-Range Weather Forecasts, Reading, United Kingdom and Peter Jan van Leeuwen, University of Reading, Meteorology, Reading, United Kingdom
Specifying High-altitude Electrons using Low-altitude LEO Systems: The SHELLS Model (399516)
Seth G Claudepierre, Aerospace Corporation Santa Monica, Santa Monica, CA, United States and Thomas Paul O'Brien III, Aerospace Corp, Corpus Christi, TX, United States
Predicting GPS TEC maps using Deep Spatio-Temporal Residual Networks (425838)
Sneha Singhania1, Bharat Kunduri2, Maimaitirebike Maimaiti3, Joseph B. H. Baker2 and J. Michael Ruohoniemi4, (1)IIIT-Bangalore, Bengaluru, India, (2)Virginia Tech, Blacksburg, United States, (3)Virginia Tech, Blacksburg, VA, United States, (4)Virginia Polytechnic Institute and State University, Blacksburg, United States
Defining the 'Typical' Coronal Mass Ejection Using Nonparametric Statistics (426199)
Douglas W Nychka, Colorado School of Mines, Applied Mathematics and Statistics, Golden, United States, Angelos Vourlidas, Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, Sarah E Gibson, National Center for Atmospheric Research, High Altitude Observatory, Boulder, CO, United States and Anna V Malanushenko, High Altitude Observatory, Boulder, United States
Automated Identification of Coronal Mass Ejections with Deep Learning (433028)
Pengyu Wang1, Yunyi Pan1, Li Feng2, Yuan Gan1, Yan Zhang1 and Lei Lu2, (1)Nanjing University, Nanjing, China, (2)Purple Mountain Observatory, Chinese Academy of Sciences, Nanjing, China

See more of: SPA-Magnetospheric Physics