NG009
Machine Learning in Space Weather

Session ID#: 159027

Session Description:
Since 2017, this session has featured the individuals, groups, and projects advancing the frontier of AI/ML in Space Weather, including all sub-disciplines of the Heliophysics and the physics of the Earth's environment. We will again bring together this community and discussion of data-driven ML applications. 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 in-painting, Bayesian inference, feature extraction, deep learning, reinforcement learning, and physics-informed machine learning.  

However, to support an evolution in our discussion and to continue to encourage cutting-edge contributions, we will theme this year's session around the progression of AI/ML in Space Weather from emerging to mature technology. That might include a focus on the scientific progress (as opposed to the ML model technical details) that contributions have created, maintenance and deployment of models (e.g., Research to Operations, R2O), responsible/ethical considerations, and AI/ML technology transfer (both within Heliophysics and across to disciplines like Earth science).

Co-Organized:
  • SA - SPA-Aeronomy
  • SH - SPA-Solar and Heliospheric Physics
  • SM - SPA-Magnetospheric Physics
Index Terms:

1942 Machine learning [INFORMATICS]
7999 General or miscellaneous [SPACE WEATHER]

Primary Convener:  Enrico Camporeale, University of Colorado/CIRES, Boulder, CO, United States
Conveners:  Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, Tomoko Matsuo, University of Colorado Boulder, Aerospace Engineering Sciences, Boulder, United States and Ryan Michael McGranaghan, ASTRA LLC, Boulder, CO, United States
 
Relationship between Microwave and EUV Emission in Solar Cycle Variations and Prediction of Solar EUV Emission Spectrum by Machine Learning Method (1130701)
Kyoko Watanabe1, Mamoru Maeda1, Shohei Nishimoto1, Shinnosuke Kitajima1, Masumi Shimojo2, Kosuke Namekata2 and Satoshi Masuda3, (1)National Defense Academy of Japan, Yokosuka, Japan, (2)National Astronomical Observatory of Japan, Mitaka, Japan, (3)Nagoya University, Institute for Space-Earth Environmental Research, Nagoya, Japan
 
Recovery of Ionospheric Signals Using Fully Convolutional DenseNet and Its Challenges (1058289)
M. Mendoza1, Aleksei V Dmitriev2, chia-Hsien Lin1 and Yu-Chi Chang, Lung-Chih Tsai, Yung-Hui Li, Mon-Chai Hsieh, Hao-Wei Hsu, Guan-Han Huang, Yu-Ciang Lin, Enkhtuya Tsogtbaatar, (1)Institute of Space Science National Central University, Jhongli, Taiwan, (2)Institute of Space Science and Engineering National Central University, Jhongli, Taiwan
 
Investigation of Data Processing and Filtering Techniques for a High-Latitude Scintillation Machine Learning Database (1198435)
Marie Bals1, Kshitija Deshpande1 and Leslie J. Lamarche2, (1)Embry-Riddle Aeronautical University, Daytona Beach, FL, United States, (2)Geophysical Institute, University of Alaska Fairbanks, Space Physics, Fairbanks, AK, United States
 
Multimodal Heliophysical/Geophysical Machine Learning Models for Earthquake Identification and Forecasting (1199484)
Debvrat Varshney1, Luke Cullen2, Asadullah Galib3, Andrew William Smith4, Edward Brown2, Peter J Chi5, Xiangning Chu6 and Filip Svoboda2, (1)University of Maryland Baltimore County, Baltimore, MD, United States, (2)University of Cambridge, Cambridge, United Kingdom, (3)Michigan State University, East Lansing, United States, (4)UCL Mullard Space Science Laboratory, Dorking, United Kingdom, (5)University of California Los Angeles, Department of Earth Planetary and Space Sciences, Los Angeles, CA, United States, (6)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States
 
Scale-aware gravity wave parameterizations for the upper atmosphere of the Earth (1053977)
Garima Malhotra, University of Colorado at Boulder, CIRES, Boulder, United States, Timothy J Fuller-Rowell, Univ of Colorado/CIRES, Boulder, CO, United States and Tzu-Wei Fang, NOAA, Space Weather Prediction Center, Boulder, United States
 
Physics-informed Machine Learning prediction of ambient solar wind speed. (1054882)
Enrico Camporeale, University of Colorado/CIRES, Boulder, CO, United States and Andong Hu, University of Colorado at Boulder, Boulder, United States
 
Predicting SWARM plasma bubbles via Machine Learning (1059788)
Sachin Reddy1, Colin Forsyth1, Anasuya L Aruliah2, Dhiren Kataria3, Gethyn Lewis1, Andrew William Smith1, Jacob Bortnik4 and Ercha Aa5, (1)UCL Mullard Space Science Laboratory, Dorking, United Kingdom, (2)University College London, Physics and Astronomy, London, United Kingdom, (3)Southwest Research Institute, San Antonio, United States, (4)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (5)MIT Haystack Observatory, Westford, United States
 
Unsupervised Clustering of Magnetospheric Dayside Data (1061953)
James Andrew Edmond, University of New Hampshire Main Campus, Durham, United States, Joachim Raeder, University of New Hampshire, Institute for the Study of Earth, Oceans, and Space, Durham, NH, United States, Banafsheh Ferdousi, University of California, Los Angeles, Los Angeles, United States, Maria Elena Innocenti, Ruhr University Bochum, Bochum, Germany and Matthew R Argall, University of New Hampshire, Durham, NH, United States
 
Innovative Uncertainty-Quantification based Ensemble Machine Learning Method on Extreme Space Weather Events (1067117)
Andong Hu, Cooperative Institute for Research in Environmental Sciences, Boulder, United States and Enrico Camporeale, University of Colorado, Boulder, United States
 
Predicting Equatorial Electron Flux Measurements from low-Earth-orbit (1067562)
Dominique LeeAnn Stumbaugh1, Seth G Claudepierre1 and Jacob Bortnik2, (1)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (2)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States
 
The Development of Spatial Attention U-Net for The Recovery of Ionospheric Measurements and The Extraction of Ionospheric Parameters (1071206)
Guan-Han Huang1, Aleksei V Dmitriev2, chia-Hsien Lin1 and Yu-Chi Chang, Mon-Chai Hsieh, Enkhtuya Tsogtbaatar, Merlin M. Mendoza, Hao-Wei Hsu, Yu-Chiang Lin, Lung-Chih Tsai, Yung-Hui Li, (1)Institute of Space Science National Central University, Jhongli, Taiwan, (2)Institute of Space Science and Engineering National Central University, Jhongli, Taiwan
 
Logistic Regression as an Alternative to Neural Networks or ARMAX for Predicting GOES-13 40-150 keV Electron Flux (1078879)
Laura E Simms, University of Michigan Ann Arbor, Ann Arbor, United States, Natalia Y Ganushkina, University of Michigan Ann Arbor, Ann Arbor, MI, United States, Max van de Kamp, Finnish Meteorological Institute, Helsinki, Finland, Michael A Balikhin, Univ Sheffield, Sheffield, United Kingdom and Michael Warren Liemohn, University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, United States
 
Developing a Neural Network for the Identification of EMIC Wave Events (1078895)
Nyssa Capman, University of Minnesota Twin Cities, Minneapolis, MN, United States, Laura E Simms, University of Michigan Ann Arbor, Ann Arbor, United States and Mark J. Engebretson, Augsburg University, Physics, Minneapolis, United States
 
Grey-Box Models for Magnetospheric Storms and Substorms (1081311)
Mikhail I. Sitnov1, Grant Killian Stephens2, Harry Arnold3, Anthony Sciola4, Kareem Sorathia1 and Viacheslav G Merkin4, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)Applied Physics Laboratory Johns Hopkins, Laurel, MD, United States, (3)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (4)The Johns Hopkins University, APL, Laurel, United States
 
Pulsating Aurora Borealis Identification Using Wavelet Scattering and Neural Networks (1081523)
Kawther Rouabhi, University of Iowa, Department of Electrical and Computer Engineering, Iowa City, IA, United States, Riley Troyer, University of Iowa, Department of Physics and Astronomy, Iowa City, United States and Allison N Jaynes, University of Iowa, Department of Physics and Astronomy, Iowa City, IA, United States
 
Opening the Black Box of the Radiation Belt Machine Learning Model (1083141)
Donglai Ma, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, Xiangning Chu, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, Seth G Claudepierre, UCLA, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, Adam C Kellerman, University of California Los Angeles, Department of Earth, Planetary, and Space Sciences, Los Angeles, CA, United States and Qianli Ma, Boston University, Boston, MA, United States
 
An active observation of aurora using a gimbal and AI in Kiruna, Sweden (1085368)
Sota Nanjo1, Urban Brandstrom2, Takuo T Tsuda1, Takeshi Aoki1 and Keisuke Hosokawa1, (1)University of Electro-Communications, Tokyo, Japan, (2)Swedish Inst. of Space Physics, Kiruna, Sweden
 
SHELLS Model: Specifying High-altitude Electrons using Low-altitude LEO Systems (1090342)
Alexander J Boyd, The Aerospace Corporation, Chantilly, United States, Janet C Green, Space Hazards Applications, LLC, Golden, United States, T. Paul O'Brien, The Aerospace Corporation, El Segundo, CA, United States and Seth G Claudepierre, University of California, Los Angeles, Santa Monica, United States
 
Three-dimensional reconstruction of ion fluxes in the Earth’s northern cusp using neural networks (1092529)
Gonzalo Cucho-Padin, NASA Goddard Space Flight Center, Greenbelt, MD, United States, David G Sibeck, NASA/GSFC, Greenbelt, United States and Benoit Lavraud, Laboratoire d'astrophysique de Bordeaux, Pessac, France
 
Prediction of Geomagnetic Auroral Electrojet Indices with Long Short-Term Memory Recurrent Neural Network (1093578)
Yucheng Shao, Winston Churchill High School, Potomac, MD, United States and A Surjalal Sharma, Univ Maryland, College Park, United States
 
Harnessing spectral continuity to isolate spacecraft reaction wheel signatures in magnetometer measurements - Implications for machine learning (1095103)
Ananya Sengupta, University of Iowa, Department of Electrical and Computer Engineering, Iowa City, United States, Allison Flores, University of Iowa, Iowa City, United States and David Miles, University of Alberta, Edmonton, AB, Canada
 
Using a Transferable Belief Model Data Fusion Method to Predict Spacecraft Charging (1096057)
Cassandra Armstrong1, Brian Larsen1 and David Gerts2, (1)Los Alamos National Laboratory, Los Alamos, NM, United States, (2)Los Alamos National Laboratory, Los Alamos, United States
 
Integrated and Interpretable Solar Flare Forecast with AIA and HMI Imaging Data: Application of the Spatial Transformer and Bayesian Neural Network (1099585)
Hu Sun, University of Michigan Ann Arbor, Ann Arbor, MI, United States, Ward Manchester, University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, MI, United States, Meng Jin, SETI Institute, Mountain View, CA, United States, Yang Liu, Stanford University, HEPL, Stanford, CA, United States and Yang Chen, University of Michigan, Department of Statistics, Ann Arbor, United States
 
Real time forecast model for the electron fluxes measured by GOES 16 (1105053)
Richard Boynton1, Michael A Balikhin2 and Simon N Walker1, (1)University of Sheffield, Sheffield, S10, United Kingdom, (2)Univ Sheffield, Sheffield, United Kingdom
 
Comparison of different approaches to a PCA-NN model for TEC with space weather parameters as predictors (1105566)
Anna L. Morozova, Teresa Barata, Tatiana Barlyaeva and Ricardo Gafeira, University of Coimbra, IA-UC, Faculty of Sciences and Technologies, Coimbra, Portugal
 
A Self-Supervised Semi-Supervised Approach to Automatic Classification of THEMIS All-Sky Images (1110834)
Donald L Hampton1, Matthew Blandin2, Dogacan Su Ozturk2, Amy M Keesee3, Hyunju KIM Connor4 and Jeremiah W Johnson5, (1)University of Alaska Fairbanks, Fairbanks, AK, United States, (2)University of Alaska Fairbanks, Fairbanks, United States, (3)University of New Hampshire, Physics and Space Science Center, Durham, NH, United States, (4)NASA Goddard Space Flight Center, Greenbelt, United States, (5)University of New Hampshire, Manchester, United States
 
Radiation Belt Electron Simulations: Combining Physics-based and Machine Learning Methods (1112919)
Adam C Kellerman1, Qianli Ma2, Frances Allana Staples3, Xiangning Chu1, Jacob Bortnik4, Kyle R Murphy5,6 and Donglai Ma7, (1)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, (2)Boston University, Boston, MA, United States, (3)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (4)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (5)Self, Canada, (6)NASA Goddard Space Flight Center, Greenbelt, United States, (7)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States
 
Single-Sensor Magnetic Interference Mitigation using Singular Spectrum Analysis and Machine Learning (1113595)
Matthew Finley and David Miles, University of Iowa, Iowa City, IA, United States
 
Emulating Coronal Magnetic Fields with Physics-Informed Neural Networks (1118785)
Nathaniel Mathews, NASA Goddard Space Flight Center, Greenbelt, MD, United States and Barbara J Thompson, NASA/GSFC, Greenbelt, MD, United States
 
Combining ML with Existing Empirical Models for Earth's Topside Ionosphere (1120586)
Shweta Dutta and Morris Cohen, Georgia Institute of Technology Main Campus, School of Electrical and Computer Engineering, Atlanta, GA, United States
 
Characterizing Geomagnetic Storm Data for Machine Learning Models of Geomagnetically Induced Currents (1120678)
Declan Baker, University of New Hampshire Main Campus, Durham, NH, United States, Victor A Pinto, University of New Hampshire Main Campus, Institute for the Study of Earth, Oceans, and Space, Durham, United States, Amy M Keesee, University of New Hampshire, Physics and Space Science Center, Durham, NH, United States and Hyunju Connor, NASA Goddard Space Flight Center, Greenbelt, United States
 
Latitudinal and Solar Cycle Variability in Efficacy of High Latitude Phase Scintillation Forecasting Using Machine Learning (1122116)
Matthew Rustad, Dayton, oh, UNITED STATES and James Caplinger, Organization Not Listed, Washington, United States
 
Creating a Cohesive Flare Prediction Dataset Using Generative Adversarial Networks (GANs) (1123437)
Allison Liu, University of Colorado at Boulder, Department of Applied Mathematics, Boulder, United States, Wendy Hawley Carande, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States and Thomas E Berger, University of Colorado at Boulder, Space Weather Technology, Research, and Education Center, Boulder, United States
 
Modeling Ring Current Proton Fluxes Using Artificial Neural Network and Van Allen Probe Measurements (1123510)
Jinxing Li1, Jacob Bortnik2, Xiangning Chu3, Donglai Ma1, Sheng Tian4 and Chih-Ping Wang5, (1)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (2)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (3)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (4)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, (5)University of California Los Angeles, Los Angeles, CA, United States
 
Active Region Coincidence Considerations in Solar Flare Prediction: Solar Cycle 24, Peak Years Study (1123825)
Christian W Hall, University of Alabama in Huntsville, Department of Computer Science, Huntsville, AL, United States, Timothy S. Newman, University of Alabama in Huntsville, Department of Computer Science, Huntsville, United States, Talwinder Singh, University of Alabama in Huntsville, CSPAR, Huntsville, AL, United States and Nikolai V Pogorelov, University of Alabama in Huntsville, Department of Space Science, Huntsville, United States
 
Global distribution and evolution of chorus waves modeled by an artificial neural network (1125880)
Xiangning Chu1, Jacob Bortnik2, Wen Li3, Xiaochen Shen3, Donglai Ma4, David Malaspina5, Qianli Ma6 and Sheng Huang6, (1)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (2)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (3)Boston University, Boston, United States, (4)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (5)University of Colorado, Astrophysical and Planetary Sciences Department, Boulder, CO, United States, (6)Boston University, Boston, MA, United States
 
Hiss in the plasmasphere and plumes: Global distribution from machine learning techniques and their effects on the loss of energetic electrons (1127704)
Sheng Huang1, Wen Li2, Xiaochen Shen2, Qianli Ma1,3, Xiangning Chu4, Donglai Ma5, Jacob Bortnik3, Luisa Capannolo1, Yukitoshi Nishimura2 and Jerry Goldstein6,7, (1)Boston University, Boston, MA, United States, (2)Boston University, Boston, United States, (3)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (4)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (5)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (6)Southwest Research Institute, San Antonio, TX, United States, (7)University of Texas at San Antonio, San Antonio, United States
 
Homogenizing Solar Extreme Ultraviolet Imaging Surveys with Uncertainty: A model-ensemble approach (1129853)
Subhamoy Chatterjee, Southwest Research Institute Boulder, Boulder, CO, United States, Andres Munoz-Jaramillo, Southwest Research Institute Boulder, Boulder, United States, Maher Dayeh, Southwest Research Institute, San Antonio, United States, Kimberly Dianne Moreland, University of Texas at San Antonio, San Antonio, TX, United States and Hazel M Bain, CIRES University of Colorado, Boulder, Boulder, CO, United States
 
Machine Learning for Ionospheric Forecasting by Emulation of Simulations and further Empirical Additions (1131304)
Liam Smith and Morris Cohen, Georgia Institute of Technology Main Campus, School of Electrical and Computer Engineering, Atlanta, GA, United States
 
Development Of An Onboard Space Weather Module For Satellite Operation (1133387)
Pavithra Ganesh Srinivas, University of South Alabama, Mobile, AL, United States and Edmund A Spencer, University of South Alabama, Electrical and Computer Engineering, Mobile, United States
 
Machine Learning Models for Ionospheric Electron Density Representation and Prediction (1134187)
Yang Pan, University of Texas at Arlington, Arlington, TX, United States, Mingwu Jin Sr, University of Texas Arlington, Arlington, United States, Shunrong Zhang, MIT Haystack Observatory, Westford, United States, Simon Wing, The Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States and Yue Deng, University of Texas Arlington, Arlington, TX, United States
 
Using LightGBMs to unveil the interplay of convection, drift, and diffusion on modulation of theGalactic Cosmic Rays (1134357)
Fadil Inceoglu, University of Colorado at Boulder, CIRES, Boulder, United States, Alessandra Abe Pacini, CU/CIRES - NOAA/NCEI, Boulder, United States and Paul T M Loto'aniu, University of Colorado, Cooperative Institute for Research in Environmental Sciences, Boulder, United States
 
The Response of Equivalent Ionospheric Currents to the External Drivers via Spatiotemporal Prediction by Neural Network (1134686)
Xin Cao, Laboratory for Atmospheric and Space Physics, Boulder, United States, Xiangning Chu, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, James M Weygand, IGPP/UCLA---ESS, Los Angeles, CA, United States, Jinxing Li, University of California, Los Angeles, Los Angeles, United States, Homayon Aryan, University of Sheffield, Sheffield, United Kingdom and Donglai Ma, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States
 
Solar flare forecast using deep reinforcement learning for imbalanced classification (1138418)
Kangwoo Yi, Kyung Hee University, Yongin, Korea, Republic of (South) and Yong-Jae Moon, School of Space Research, Kyung Hee University, Yongin, South Korea
 
Reconstruction of the regional total electron content maps over the Korean Peninsula using deep convolutional generative adversarial network and Poisson blending (1138896)
Se-Heon Jeong1, Woo Kyoung Lee2, Soojeong Jang2, Hyosub Kil3, Jeong-Heon Kim4, Young-Sil Kwak5, Yongha Kim4, Junseok Hong6 and Byung-Kyu Choi2, (1)Chungnam National University, Daejeon, Korea, Republic of (South), (2)Korea Astronomy and Space Science Institute, Daejeon, South Korea, (3)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (4)Chungnam National University, Daejeon, South Korea, (5)KASI Korea Astronomy and Space Science Institute, Daejeon, South Korea, (6)KASI Korea Astronomy and Space Science Institute, Daejeon, Korea, Republic of (South)
 
TIE-GCM Emulation using LSTM-based Reduced Order Model with Uncertainty Quantification (1147480)
Richard Licata and Piyush Mehta, West Virginia University, Morgantown, WV, United States
 
Empirical parametrization of SSUSI-derived auroral ionization rates (1148379)
Stefan Bender, Norwegian University of Science and Technology, Department of Physics, Trondheim, Norway, Patrick J Espy, NTNU, Trondheim, Norway and Larry J Paxton, The Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States
 
Understanding the Dissipation of Different Scale Solar Wind Magnetic Structures Using Information Theory (1148867)
Katherine Holland, Embry-Riddle Aeronautical University, Daytona Beach, FL, United States, Katariina Nykyri, Embry-Riddle Aeronautical Univ, Daytona Beach, FL, United States, Xuanye Ma, University of Alaska Fairbanks, Fairbanks, United States and Simon Wing, The Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States
 
The MAGICIAN Project: Machine Learning, Data Collection, and Education for Space Science Research (Invited) (1149174)
Amy M Keesee, University of New Hampshire, Physics and Space Science Center, Durham, NH, United States, Hyunju Connor, NASA Goddard Space Flight Center, Greenbelt, United States and MAGICIAN Team
 
Generative Deep Learning with High-Resolution SDO EUV Images of the Sun (1149488)
Frederic Effenberger1, Mehdi Cherti2, Stefan Kesselheim2, Ruggero Vasile3 and Jenia Jitsev2, (1)Ruhr University Bochum, Bochum, Germany, (2)Forschungszentrum Julich GmbH, JSC, Julich, Germany, (3)Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences, Geosciences, Potsdam, Germany
 
Merging Short and Long Lead-time Dst Probabilistic Forecasts (1149585)
Brian Michael Swiger1, Enrico Camporeale2, Andong Hu1 and W. Kent Tobiska3, (1)University of Colorado, CIRES, Boulder, United States, (2)University of Colorado, Boulder, United States, (3)Space Environment Technologies, Pacific Palisades, CA, United States
 
Forecasting Solar Flares with a New Topological Parameter and a Supervised Machine-learning Method (1149643)
Luca Giovannelli1, Francesco Berrilli1, Dario Del Moro1, Domenico Cicogna2, Daniele Calchetti3, Feredico Benvenuto4, Cristina Campi4, Sabrina Guastavino4 and Michele Piana4, (1)University of Rome Tor Vergata, Physics, Rome, Italy, (2)NEXT Ingegneria dei Sistemi S.p.A, Rome, Italy, (3)Max Planck Institute for Solar System Research, Katlenburg-Lindau, Germany, (4)University of Genoa, Department of Mathematics, Genoa, Italy
 
Determination of 3-D parameters of coronal mass ejections using CNN models (1151764)
Hyeonock Na and Yong-Jae Moon, School of Space Research, Kyung Hee University, Yongin, South Korea
 
Machine Learning Algorithms for the Detection of Plasmoids in Multiple-X-Line Collisionless Reconnection Regions (1152103)
Kendra Bergstedt, Princeton University, Princeton, NJ, United States and Hantao Ji, Princeton Plasma Physics Laboratory, Princeton, NJ, United States
 
Machine Learning for solving the Bz Problem in Space Weather Forecasting (1153138)
Hannah Rüdisser1, Martin Reiss2,3, Christian Moestl4, Tanja Amerstorfer4, Ute Amerstorfer1, Andreas Weiss4,5, Rachel Bailey6, Andreas Windisch7, Jürgen Hinterreiter8, Siegfried Gonzi9 and David Jackson9, (1)ZAMG Central Institution for Meteorology and Geodynamics, Austrian Space Weather Office, Graz, Austria, (2)Community Coordinated Modeling Center, Code 674, NASA GSFC,, Greenbelt, United States, (3)Austrian Space Weather Office, Central Institution for Meteorology and Geodynamics, Graz, Austria, (4)Austrian Space Weather Office, ZAMG Central Institution for Meteorology and Geodynamics, Graz, Austria, (5)Heliophysics Science Division, NASA Goddard Space Flight Center, Greenbelt, United States, (6)ZAMG Central Institution for Meteorology and Geodynamics, Conrad Observatory, Vienna, Austria, (7)Know-Center GmbH, Graz, Austria, (8)University of Graz, Institute of Physics, Graz, Austria, (9)Met Office, Exeter, United Kingdom
 
Physics Informed Neural Networks for Solar Magnetic Field Simulations (1153792)
Robert Jarolim, University of Graz, Graz, Austria, Julia K Thalmann, Institute for Physics/IGAM, University of Graz, Graz, Austria, Astrid Veronig, University of Graz, Institute of Physics, Graz, Austria, Tatiana Podladchikova, Skolkovo Institute of Science and Technology, Skolkovo, Russia and Benoit Tremblay, University of Montreal, Physics department, Montreal, QC, Canada
 
Forecast Global Ionospheric TEC Using Modified U-Net and VISTA TEC Dataset (1154414)
Zihan Wang1, Shasha Zou1, Hu Sun2 and Yang Chen3, (1)University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, MI, United States, (2)University of Michigan Ann Arbor, Ann Arbor, MI, United States, (3)University of Michigan, Department of Statistics, Ann Arbor, United States
 
In Search of a Data Driven Symbolic Multi-Fluid 10-Moment Model Closure (1154418)
John Donaghy, University of New Hampshire Main Campus, Durham, NH, United States and Kai Germaschewski, University of New Hampshire, Durham, NH, United States
 
Time-oversampling and regression as a training framework to mitigate the data scarcity and class imbalances problem in the forecast of strong flares with deep learning (1157909)
Gregoire Francisco1, Dario Del Moro1, Teresa Barata2 and João Manuel Fernandes3, (1)University of Rome Tor Vergata, Physics, Rome, Italy, (2)University of Coimbra, IA-UC, Faculty of Sciences and Technologies, Coimbra, Portugal, (3)University of Coimbra, CITEUC, Coimbra, Portugal
 
Early EUV irradiance forecast using virtual spacecraft outside the Sun-Earth viewpoint (1158690)
Benoit Tremblay, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, Robert Jarolim, University of Graz, Graz, Austria, Miraflor Santos, Woods Hole Oceanographic Institution, Woods Hole, United States, Margarita Bintsi, Imperial College London, Computing, London, United Kingdom, Anna Jungbluth, University of Oxford, Oxford, United Kingdom, Andres Munoz-Jaramillo, Montana State University, Bozeman, United States, James P. Mason, Johns Hopkins University Applied Physics Laboratory, Laurel, United States and Angelos Vourlidas, Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States
 
Hierarchical Classification of Solar Flares, Coronal Mass Ejections, Interplanetary Shocks and Solar Wind Plasma Properties in Predicting the Peak Intensity of Energetic Storm Particle Events (1158802)
Kimberly Dianne Moreland, University of Texas at San Antonio, San Antonio, TX, United States, Maher Dayeh, Southwest Research Institute, San Antonio, United States and Subhamoy Chatterjee, Southwest Research Institute, Boulder, CO, United States
 
Machine Learning Approach to Identifying Flux Rope Orientation (1159488)
Jack Topper, Frederick, Maryland, UNITED STATES, Thomas Narock, Goucher College, Center for Data, Mathematical, and Computational Sciences, Baltimore, United States, Teresa Nieves-Chinchilla, NASA Goddard Space Flight Center, Heliophysics Science Division, Greenbelt, United States, Sanchita Pal, George Mason University, Fairfax, United States and Luiz F. G. dos Santos, Shell Global Solutions, Houston, United States
 
A Monte Carlo Markov Chain Approach to the Probabilistic Drag Based Model for Coronal Mass Ejection Propagation (1159599)
Simone Chierichini1,2, Teresa Barata3, Enrico Camporeale4, Dario Del Moro1, Giancarlo De Gasperis1, Robertus Erdelyi2, João Manuel Fernandes5, Raffaello Foldes6,7, Gregoire Francisco1, Luca Giovannelli1, Ronish Mugatwala1,2, Gianluca Napoletano1,8, Ajay Tiwari9 and Jannis Teunissen9, (1)University of Rome Tor Vergata, Physics, Rome, Italy, (2)University of Sheffield, School of Mathematics and Statistics, Sheffield, United Kingdom, (3)University of Coimbra, IA-UC, Faculty of Sciences and Technologies, Coimbra, Portugal, (4)University of Colorado, Boulder, United States, (5)University of Coimbra, CITEUC, Coimbra, Portugal, (6)University of L'Aquila, Department of Physical and Chemical Sciences, L'Aquila, Italy, (7)École Centrale de Lyon, Laboratoire de Mécanique des Fluides et Acoustique, Lyon, France, (8)University of L'Aquila, L'Aquila, Italy, (9)Centrum Wiskunde & Informatica, Amsterdam, Netherlands
 
Correcting ArcJet Contamination to GOES-16 MAG using Bi-Directional LSTM Networks with Luong Attention (1160252)
Fadil Inceoglu1, Alison Jarvis2, Paul T M Loto'aniu3, Aspen Davis4 and Alessandra Abe Pacini4, (1)University of Colorado at Boulder, CIRES, Boulder, United States, (2)CIRES/CU NOAA/NCEI, Boulder, CO, UNITED STATES, (3)University of Colorado, Cooperative Institute for Research in Environmental Sciences, Boulder, United States, (4)CU/CIRES - NOAA/NCEI, Boulder, United States
 
Prediction of the occurrence of solar energetic particle events using machine learning on measurements of coronal mass ejections (1161535)
Ming Zhang1, Peter Tarsoly2, Jesse Torres2, Peter Thomas1 and Philip Chan2, (1)Florida Institute of Technology, Melbourne, United States, (2)Florida Institute of Technology, Melbourne, FL, United States
 
Pushing the Frontiers of Operational Geoelectric Hazard Modeling (1162857)
Gabriel Moraga, Boulder, Colorado, UNITED STATES, Greg Lucas, Univ of Colorado, Boulder, United States, Wendy Hawley Carande, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States and Erin Joshua Rigler, USGS, Denver, CO, United States
 
Statistical Analysis of Plasmaspheric Erosion and Refilling – Machine Learning Approach (1163571)
James Lende1, Xiangning Chu1, Jacob Bortnik2, Max Doering1, Xin Cao3, Donglai Ma4 and Richard Eugene Denton5, (1)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (2)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (3)Laboratory for Atmospheric and Space Physics, Boulder, United States, (4)University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (5)Dartmouth College, Department of Physics and Astronomy, Hanover, United States
 
Dynamics of Plasmaspheric Ions Modeled by a Neural Network (1165903)
Max Doering, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, Xiangning Chu, University of California Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, James Lende, Colorado School of Mines, Golden, CO, United States, Jerry Goldstein, Southwest Research Institute, San Antonio, United States, Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States and Naomi Maruyama, University of Colorado, LASP, Boulder, United States
 
A Machine Learning Approach to Identifying Magnetic Impulses in Geospace Data (1166485)
Brandon Zhao, University of California Los Angeles, Los Angeles, CA, United States and Peter J Chi, University of California Los Angeles, Department of Earth Planetary and Space Sciences, Los Angeles, CA, United States
 
Forecasting relativistic electron fluxes of the Earth's radiation belt using machine learning (1167582)
Ankush Tukaram Bhaskar, Space Physics Laboratory, Vikram Sarabhai Space Centre, Indian Space Research Organisation, Trivandrum, India, Karthik Amaravadi, University of Alabama at Birmingham, Birmingham, United States, Baiju Dayanandan, University of Nizwa, Department of Mathematical and Physical Sciences, College of Arts and Science, Nizwa, Oman and Tarun K Pant, Space Physics Laboratory,Vikram Sarabhai Space Centre,Indian Space Research Organaisation, Trivandrum, India
 
Effects of Driving Parameter Filtering on SWPSNN Model Performance (1170692)
Aaron Mark Johnson, Gustavus Adolphus College, Saint Peter, MN, United States, Michael Warren Liemohn, University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, United States and Brian Michael Swiger, University of Michigan, Climate and Space Sciences and Engineering, Ann Arbor, MI, United States
 
Near Real-time Validation of the Magstar Magnetometer Array: Challenges, Requirements and Techniques (1170992)
Sudha Kapali, Computational Physics Inc., Lowell, MA, United States, Jennifer L Gannon, Computational Physics Inc. Boulder, Boulder, United States, Michael Henderson, Sun Dog Scientific LLC, Springfield, VA, United States and Jurgen Matzka, Leomagnetics GmbH, Bad Doberan, Germany
 
Forecasting Ground Magnetic Perturbations at High and Mid-Latitudes Using Deep Learning and Near Real-Time Solar Wind Data (1175128)
Victor A Pinto, University of New Hampshire Main Campus, Institute for the Study of Earth, Oceans, and Space, Durham, United States; Universidad de Santiago de Chile, Physics, Santiago, Chile, Amy M Keesee, University of New Hampshire, Physics and Space Science Center, Durham, NH, United States, Michael Coughlan, University of New Hampshire Main Campus, Durham, United States, Raman Mukundan, University of New Hampshire Main Campus, Durham, NH, United States, Jeremiah W Johnson, University of New Hampshire, Manchester, United States and Hyunju KIM Connor, University of Alaska Fairbanks, Fairbanks, United States; NASA Goddard Space Flight Center, Greenbelt, United States
 
On the Variation of Column O/N2 in the upper atmosphere using Principal Component Analysis in 2-dimensional images (1189191)
Divyam Goel1, Yen-Jung Wu1, Brian J Harding2, Colin Charles Triplett2, Thomas J Immel1, Chihoko Y Cullens3 and Scott England4, (1)University of California Berkeley, Space Sciences Laboratory, Berkeley, CA, United States, (2)University of California, Berkeley, Space Sciences Laboratory, Berkeley, United States, (3)University of Colorado at Boulder, Laboratory for Atmospheric and Space Physics, Boulder, United States, (4)Virginia Polytechnic Institute and State University, Aerospace and Ocean Engineering, Blacksburg, VA, United States
 
Identifying Flank-Crossing of Interplanetary Coronal Mass Ejections with a Deep Convolutional Neural Network (1190808)
Mark Chiriac1,2, Sanchita Pal2,3, Thomas Narock4, Luiz F. G. dos Santos5, Ayris Narock2,6 and Teresa Nieves-Chinchilla2, (1)Massachusetts Institute of Technology, Cambridge, MA, United States, (2)NASA Goddard Space Flight Center, Heliophysics Science Division, Greenbelt, United States, (3)George Mason University, Fairfax, United States, (4)Goucher College, Center for Data, Mathematical, and Computational Sciences, Baltimore, United States, (5)Shell Global Solutions, Houston, United States, (6)ADNET Systems Inc., Greenbelt, United States
 
Detecting Sporadic E Using Supervised Learning Model (1190953)
Joseph Ellis, Georgia Institute of Technology, Powder Springs, GA, UNITED STATES, Morris Cohen, Georgia Institute of Technology Main Campus, School of Electrical and Computer Engineering, Atlanta, GA, United States and Daniel Emmons, Air Force Institute of Technology, Department of Engineering Physics, Wpafb, United States
 
Machine Learning (ML) Bloopers – What not to do when creating ML models (1191399)
Natasha Flyer, Flyer Research LLC, Boulder, United States, Thomas Berger, University of Colorado Space Weather Technology, Research, and Education Center, Boulder, CO, United States, Kiera van der Sande, University of Colorado at Boulder, Applied Mathematics, Boulder, United States, Allison Liu, Laboratory for Atmospheric and Space Physics, Boulder, United States and Varad Deshmukh, University of Colorado Boulder, Computer Science, Boulder, United States
 
A Novel Reduction-Based Scheme for In-Situ Solar Wind Origin Classification using Machine Learning (1191615)
Daniel Carpenter, University of Michigan Ann Arbor, Ann Arbor, MI, United States, Susan T Lepri, University of Michigan, Ann Arbor, MI, United States; University of Michigan Ann Arbor, Ann Arbor, United States, Liang Zhao, University of Michigan, Ann Arbor, United States and Henry Han, Baylor University, Waco, United States
 
Sequence to Sequence Learning for Solar Wind Dynamics (1191768)
Charles Topliff, Georgia Institute of Technology Main Campus, Atlanta, GA, United States and Morris Cohen, Georgia Institute of Technology Main Campus, School of Electrical and Computer Engineering, Atlanta, GA, United States
 
Physics-Informed Neural Networks for Modeling of Space Plasmas (1192808)
Eric Lee Winter, George Mason University Fairfax, Fairfax, United States and Robert S Weigel, George Mason University, Fairfax, VA, United States
 
Predicting Ionospheric Dynamics At Low Latitudes Using Neural Networks: Applications to Ionogram and Spread-F Forecasting (1193398)
Enrique Luis Alfonso Rojas Villalba, Cornell University, Ithaca, NY, United States, Jhassmin Aricoché Del Campo, Instituto Geofísico del Perú, Jicamarca Radio Observatory, Lima, Peru, Reynaldo Rojas, Universidad de Ingeniería y Tecnología, Lima, Peru and Marco Milla, Pontifical Catholic University of Peru, Lima, Peru
 
Estimation of Quasi-Thermal Noise Plasma Parameters using Convolutional Neural Networks (1193457)
Ayushmaan Aggarwal1, Trevor Bowen2 and Marc Pulupa1, (1)Space Sciences Laboratory, University of California Berkeley, Berkeley, CA, United States, (2)University of California Berkeley, Berkeley, CA, United States
See more of: Nonlinear Geophysics
<< Previous Session Proposal | Next Session Proposal >>