SM31D:
Machine Learning in Space Weather I Posters


Submit an Abstract to this Session


Session ID#: 45586

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:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States and Enrico Camporeale, University of Colorado, Queen Mary University of London, Boulder, United States
OSPA Liaison:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States
Co-Organized with:
SPA-Magnetospheric Physics, SPA-Solar and Heliospheric Physics, and SPA-Aeronomy

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:

Using Random Forest Algorithm to Predict Flare Index of Active Regions (414895)
William Branca, Yorktown High School, Yorktown Heights, NY, United States
A deep learning approach to forecast tomorrow's solar wind parameters. (350972)
Carl Shneider, Center for Mathematics and Computer Science (CWI), Multiscale Dynamics, Amsterdam, Netherlands, Mandar Chandorkar, Centrum Wiskunde & Informatica, Amsterdam, Netherlands, Monica Bobra, Stanford-HEPL Solar Physics, Stanford, CA, United States and Enrico Camporeale, University of Colorado, Queen Mary University of London, Boulder, United States
Quantitative Prediction of High-Energy Electron Integral Fluxat Geostationary Orbit Based on Deep Learning (353823)
Qiuzhen Zhong, National Space Science Center, Chinese Academy of Sciences, Beijing, China, Lihang Wei, University of Chinese Academy of Sciences, Beijing, China, Ruilin Lin, National Space Science Center, Beijing, China and Siqing Liu, Chinese Academy of Sciences, National Space Science Center, Beijng, China
Bayesian Inference of Radial Diffusion Parameters for the Earth's Radiation Belt: a Deep Learning Framework (355592)
Rakesh Sarma1, Mandar Chandorkar1, Enrico Camporeale2, Alexander Drozdov3 and Yuri Shprits3, (1)Centrum Wiskunde & Informatica, Amsterdam, Netherlands, (2)University of Colorado, Queen Mary University of London, Boulder, United States, (3)University of California Los Angeles, Los Angeles, United States
Generation of solar magnetograms and EUV images of Galileo sunspots by deep learning (366711)
Harim Lee1, Yong-Jae Moon1, Eunsu Park2 and Taeyoung Kim1,3, (1)School of Space Research, Kyung Hee University, Yongin, South Korea, (2)Department of Astronomy & Space Science, Kyung Hee University, Yongin, South Korea, (3)InSpace Co., Ltd., Taejon-City, Korea, Republic of (South)
Generation of Solar EUV images from HMI magnetograms by deep learning (366791)
Eunsu Park1, Yong-Jae Moon2, Harim Lee2 and Taeyoung Kim2,3, (1)Department of Astronomy & Space Science, Kyung Hee University, Yongin, South Korea, (2)School of Space Research, Kyung Hee University, Yongin, South Korea, (3)InSpace Co., Ltd., Taejon-City, Korea, Republic of (South)
Global magnetosphere modeling with empirical ring current pressure (383083)
Viacheslav G Merkin1, Mikhail I. Sitnov2, Kareem Sorathia2, Grant Stephens3, Aleksandr Y Ukhorskiy4 and John Lyon5, (1)Johns Hopkins University, Baltimore, MD, United States, (2)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (3)Applied Physics Laboratory Johns Hopkins, Laurel, MD, United States, (4)JHU/APL, Laurel, United States, (5)Dartmouth College, Hanover, NH, United States
Using Machine-Learning Methods and Expert Prediction Probabilities to Forecast Solar Flares (384834)
Viacheslav M Sadykov, Georgia State University, Physics & Astronomy, Atlanta, GA, United States; Georgia State University, Atlanta, GA, United States, Alexander G Kosovichev, New Jersey Institute of Technology, Physics, Newark, United States; NASA Ames Research Center, Moffett Field, United States and Irina Kitiashvili, NASA Ames Research Center, Moffett Field, CA, United States; Bay Area Environmental Research Institute, Moffett Field, CA, United States
Machine Learning Algorithms for Spacecraft Magnetic Field Interference Cancellation: Enabling Satellite Magnetometry without a Boom (386421)
Mark B. Moldwin, Srinagesh Sharma and James Cutler, University of Michigan Ann Arbor, Ann Arbor, MI, United States
Forecasting solar flare occurrence based on Convolutional Neural Network using SDO/HMI magnetograms and the flare occurrence of the previous day (388664)
Seulki Shin1, Yong-Jae Moon1 and Hyoungseok Chu2, (1)School of Space Research, Kyung Hee University, Yongin, South Korea, (2)Software Policy & Research Institute, Seongnam-si, South Korea
Weakly- and Semi-Supervised Semantic Segmentation for Aurora Image Classification (390642)
Chuang Niu1, Shenghan Ren1, Haihong Hu1, Han Desheng2, Zejun Hu2 and Jimin Liang1, (1)Xidian University, Xi'an, China, (2)Polar Research Institute of China, Shanghai, China
Using Machine Learning Models for Space Weather with the Divide and Conquer Approach (393944)
Jorge Amaya, Katholieke Universiteit Leuven, Leuven, Belgium and Giovanni Lapenta, KU Leuven, Mathematics, Leuven, Belgium
Classifying SuperDARN Backscatter using Machine Learning Algorithms (395235)
Esther Robb1, Xueling Shi2, Shibaji Chakraborty, PhD2, J. Michael Ruohoniemi2, Joseph B. H. Baker2 and Maimaitirebike Maimaiti1, (1)Virginia Tech, Blacksburg, VA, United States, (2)Virginia Tech, Blacksburg, United States
Effects of Data Binning Techniques on Results of Analyzing Solar Wind and Geomagnetic Indices Data (396419)
Shing F Fung, NASA Goddard Space Flight Center, Greenbelt, United States and Andrew Zheng, River Hill High School, Clarksville, United States
Automating the McIntosh Classification System using Machine Learning (398670)
Andrew R Jones, University of Colorado at Boulder, Boulder, CO, United States, Megan Claire Smith, Laboratory for Atmospheric and Space Physics, Boulder, United States and Laura Sandoval, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States
Automatic detection of ICMEs at 1 AU : a deep learning approach (404625)
Gautier Nguyen, DGA, Paris, France, Nicolas Aunai, Laboratoire de Physique des Plasmas, CNRS, Paris, France, Dominique Fontaine, Laboratoire de Physique des Plasmas (LPP), CNRS, Observatoire de Paris, Sorbonne Université, Université Paris-Saclay, Ecole polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France, Palaiseau, France, Erwan Le Pennec, Centre de Mathématiques Appliqués, Ecole polytechnique, Palaiseau, France and Alexis Jeandet, Laboratoire de Physique des Plasmas, Palaiseau, France
Solar Image Deconvolution by Generative Adversarial Network (407322)
Long Xu, Chinese Academy of Sciences, Beijing, China, Yihua Yan, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, China and Wenqing Sun, CAS Chinese Academy of Sciences, Beijng, China
How can machine learning help us to analyze CME's data? (439601)
Luiz Fernando Guedes dos Santos, Catholic University of America, Washington, DC, United States, Teresa Nieves-Chinchilla, NASA Goddard Space Flight Center, Heliophysics Science Division, Greenbelt, MD, United States, Barbara J Thompson, NASA GSFC, Greenbelt, United States and Michael S Kirk, Atmospheric and Space Technology Research Associates, LLC, Boulder, United States
Mulitiscale 3D structure of substorm currents obtained by mining spaceborne magnetometer data (445673)
Grant Killian Stephens1, Mikhail I. Sitnov1, Haje Korth1, Shinichi Ohtani2, Matina Gkioulidou1 and Sasha Ukhorskiy1, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)JHU/APL, Laurel, United States
Systematic Analysis of ML Techniques for Kp Prediction (449726)
Yuri Shprits, GFZ German Research Centre for Geosciences, Potsdam, Germany, Irina S S Zhelavskaya, Organization Not Listed, Washington, United States and Ruggero Vasile, Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences, Geosciences, Potsdam, Germany
DeepEM: A Deep Neural Network for DEM Inversion (457182)
Paul James Wright, University of Glasgow, Glasgow, G12, United Kingdom, Richard Galvez, New York University, New York, NY, United States, Alexandre Szenicer, University of Oxford, Oxford, United Kingdom, Rajat Thomas, University of Amsterdam, Amsterdam, Netherlands, Meng Jin, SETI Institute, Mountain View, United States, David Fouhey, University of California, Berkeley, Berkeley, United States, Chun Ming Mark Cheung, CSIRO Astronomy and Space Science Geraldton, Perth, Australia, Andrés Muñoz-Jaramillo, Southwest Research Institute Boulder, Boulder, CO, United States and Graham Mackintosh, NASA Frontier Development Lab, Mountain View, CA, United States
Feature Engineering for Deep Learning to Forecast Solar Events (459249)
Maxine Hartnett1, Justin Cai1, Wendy Hawley Carande1, James Craft2, Andrew R Jones3, Kim Kokkonen1, Tracey Morland4 and Laura Sandoval1, (1)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (2)University of Colorado, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (3)Laboratory for Atmospheric and Space Physics, University of Colorado Boulder, Boulder, United States, (4)Laboratory for Atmospheric and Space Physics, Boulder, United States
Machine Learning based Prediction of Filament Eruptions using Automated Detection & Tracking Technique (460463)
Anand D Joshi and Yoichiro Hanaoka, NAOJ National Astronomical Observatory of Japan, Tokyo, Japan
Solar Flare Forecasting: A Novel Deep Learning Approach (463669)
Justin Cai1, Wendy Hawley Carande1, James Craft2, Maxine Hartnett1, Andrew R Jones3, Kim Kokkonen1, Tracey Morland4 and Laura Sandoval1, (1)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (2)University of Colorado, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (3)Laboratory for Atmospheric and Space Physics, University of Colorado Boulder, Boulder, United States, (4)Laboratory for Atmospheric and Space Physics, Boulder, United States
Predicting energetic storm particle (ESP) properties near 1 AU (466620)
Jacob Nickell1, Maher A Dayeh2 and Mihir Indrajit Desai2, (1)University of Texas at San Antonio, Physics and Astronomy, San Antonio, TX, United States, (2)Southwest Research Institute, San Antonio, United States

See more of: SPA-Magnetospheric Physics