Machine Learning in Space Weather
Machine Learning in Space Weather
Session ID#: 119066
Session Description:
Advances in ML have been fueled by the growth of available data and ubiquity of capable computing technologies. Space physics and geophysics are characterized by impressive amounts of freely-available data and can certainly benefit from data-driven ML applications.
This session will focus on applications of Machine Learning to Space Weather problems across all sub-disciplines of the Heliophysics and the physics of the Earth's environment, including the coupling of the interplanetary plasma with the upper atmosphere. Contributions ranging from black-box models to data-driven physics-based simulations are welcome, including (but not limited to) regression and classification problems, inverse problems, dimensionality reduction, automatic event identification, data augmentation and inpainting, Bayesian inference, feature extraction, deep learning, reinforcement learning, and physics-informed machine learning.
Co-Organized:
- SA - SPA-Aeronomy
- SH - SPA-Solar and Heliospheric Physics
- SM - SPA-Magnetospheric Physics
Co-Sponsor(s):
- AMS: American Meteorological Society -
- EGU: European Geosciences Union -
Index Terms:
1914 Data mining [INFORMATICS]
1942 Machine learning [INFORMATICS]
4460 Pattern formation [NONLINEAR GEOPHYSICS]
7924 Forecasting [SPACE WEATHER]
Primary Convener: Enrico Camporeale, University of Colorado at Boulder, Boulder, United States
Conveners: Jacob Bortnik, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, Tomoko Matsuo, University of Colorado Boulder, Boulder, CO, United States and Ryan Michael McGranaghan, Atmospheric and Space Technology Research Associates (ASTRA), Louisville, CO, United States
Primary Liaison: Enrico Camporeale, University of Colorado, Cooperative Institute for Research in Environmental Sciences, Boulder, United States
See more of: Nonlinear Geophysics