Artificial Intelligence (AI) for scientific discovery in Solar Wind-Earth Interaction

Chu, Xiangning

SM002
Artificial Intelligence (AI) for scientific discovery in Solar Wind-Earth Interaction

Session ID#: 248736

Session Description:

Artificial Intelligence (AI) is rapidly transforming how we explore and understand the Sun-Earth system. This session highlights cutting-edge applications of AI in Heliophysics and showcases how these tools are opening new frontiers in scientific discovery. We invite contributions that demonstrate the applications of AI methods on solving fundamental challenges across solar wind, magnetosphere, ionosphere, thermosphere, and mesosphere. We encourage innovative showcases integrating AI with traditional scientific approaches, such as theory, first-principle simulations, empirical models, and statistical or event-based analyses. Submissions involving data-driven deep learning, interpretable machine learning, physics-informed-neural-networks (PINNs), and AI-guided solutions to partial differential equations (PDEs) are also encouraged. By bridging together AI innovators and domain experts, this session aims to foster a collaborative environment that accelerates discovery and deepens our understanding of Sun-Earth interactions. This session is organized in collaboration with Machine-Learning-based Geospace Environment Modeling (MLGEM) focus group, with the goal of building synergy across the Heliophysics community.

Index Terms:

2427 Ionosphere/atmosphere interactions [IONOSPHERE]
2431 Ionosphere/magnetosphere interactions [IONOSPHERE]
2784 Solar wind/magnetosphere interactions [MAGNETOSPHERIC PHYSICS]
2788 Magnetic storms and substorms [MAGNETOSPHERIC PHYSICS]

Primary Convener: Dr. Xiangning Chu, Laboratory for Atmospheric and Space Physics, Boulder, United States

Conveners: Sai Gowtam Valluri, NASA Goddard Space Flight Center, Greenbelt, United States, Matthew R Argall, University of New Hampshire, Durham, United States and Dr. Banafsheh Ferdousi, PhD, University of California, Los Angeles, Los Angeles, United States

Student/Early Career Convener: Brianna Isola, University of New Hampshire Main Campus, Durham, United States

2D Reconstruction from Measurements Along a Space Trajectory Using SIREN-Enhanced Physics-Informed Neural Networks (PINNs) (1953641)

Eunjin Choi¹, Hiroshi Hasegawa², Kyoung-Joo Hwang³, Kyunghwan Dokgo³ and James Burch¹, (1)Southwest Research Institute, San Antonio, TX, United States, (2)Japan Aerospace Exploration Agency, Institute of Space and Astronautical Science, Sagamihara, Japan, (3)Southwest Research Institute, San Antonio, United States

Automated Detection of Electron-Scale Magnetic Reconnection in Earth’s Magnetosheath Using Machine Learning Tools (1983449)

Yilan Qin, Chuanfei Dong, Xinmin Li and Raul Lama, Boston University, Boston, United States

Can We Predict Super Substorms? IRANNA: An Imbalanced Regression Neural Network for Auroral Electrojet Indices (1936484)

Dr. Xiangning Chu, Laboratory for Atmospheric and Space Physics, Boulder, United States, Lucas Jia, University of California Santa Barbara, Department of Electrical & Computer Engineering, Santa Barbara, CA, United States, Robert L McPherron, Univ Calif Los Angeles, Los Angeles, CA, United States, Xinlin Li, Beihang University, Beijing, China and Jacob Bortnik, University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States

Characterizing Earth's Plasma Sheet through Multi-Spacecraft Observations and Machine Learning (1879200)

Savvas Raptis¹, Connor O'Brien², Kareem Sorathia³, Viacheslav G Merkin¹, Louis Richard⁴ and Simon Wing⁵, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)University of Minnesota, Minneapolis, United States, (3)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (4)IRF Swedish Institute of Space Physics Uppsala, Uppsala, Sweden, (5)The Johns Hopkins University Applied Physics Laboratory, Laurel, United States

Enhancing Thermospheric Forecasts using Ensemble Models in the ROPE Framework (1895542)

Anirudh Tapedia and Piyush Mehta, West Virginia University, Morgantown, United States

Evaluating Auroral Boundary Predictions Using Machine Learning–Based Particle Precipitation Model (1934343)

Arsad Refat¹, Sai Gowtam Valluri², Hyunju KIM Connor², Yang He³, M. Chantale Damas³ and NASA GSFC, (1)Baruch College, Queens Village, NY, UNITED STATES, (2)NASA Goddard Space Flight Center, Greenbelt, United States, (3)CUNY Queensborough Community College, Bayside, United States

Heating and Cooling process of Plasma sheet at lunar plasma environment: Inferred from ARTEMIS Observation (1991829)

Dr. Ephrem Tesfaye Desta, PhD, North-West University, Center for Space Research and Addis Ababa University, Physics Department, Addis Ababa, Ethiopia, Du Toit Strauss, North West University, Center for Space Research, Potchefstroom, South Africa and Nicholas Eugene Engelbrecht, North-West University, Potchefstroom, South Africa

High Latitude Ionospheric Prediction and Forcing Deconvolution: A Tree-Based Machine Learning Approach using PFISR and SD-WACCM-X / MERRA2 (1967232)

Benjamin Martinez¹, Xian Lu¹, Lindsay Goodwin² and Colin Arcaro³, (1)Clemson University, Physics and Astronomy, Clemson, SC, United States, (2)New Jersey Institute of Technology, Newark, United States, (3)New Jersey Institute of Technology, Edison, NJ, United States

Implementation of a Regression Model for Ion Fluxes in the Low-Altitude Earth's Northern Cusp Using In-Situ DMSP/SSJ Data and a Residual Neural Network (1857125)

Shaimaa Al-Zaman¹, Gonzalo Cucho-Padin², David G Sibeck³, Daniel da Silva⁴, Cristian Ferradas⁵, Hyunju KIM Connor⁶, Sai Gowtam Valluri⁶, Xueyi Wang⁷, Xiaolei Li⁸, Bo Shen⁹ and Qin Li¹⁰, (1)New Jersey Institute of Technology, Edison, NJ, United States, (2)Catholic University of America, Washington, United States, (3)NASA/GSFC, Greenbelt, United States, (4)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (5)NASA Goddard Space Flight Center, Heliophysics Division, Greenbelt, United States, (6)NASA Goddard Space Flight Center, Greenbelt, United States, (7)Auburn University, Physics Department, Auburn, AL, United States, (8)Auburn University, Physics, Auburn, United States, (9)New Jersey Institute of Technology, Institute for Space Weather Sciences, Newark, United States, (10)Institute for Space Weather Sciences, New Jersey Institute of Technology, Newark, NJ, United States

Innovative Integration of Deep Learning and Physics-Based Models for Simulating Global Electron Precipitation Driven by Whistler-mode Waves (1897717)

Fira Fatmasiefa¹, Wen Li¹, Luisa Capannolo², Xiaochen Shen², Qianli Ma², Sheng Huang¹, Dr. Xiangning Chu³ and Van Allen Probes Team, THEMIS Team, (1)Boston University, Boston, MA, United States, (2)Boston University, Boston, United States, (3)Laboratory for Atmospheric and Space Physics, Boulder, United States

Integration of Kinetic Effects into Multi-Moment Multifluid Models through Machine Learning (Invited) (1851153)

Chuanfei Dong¹, Ziyu Huang², Yilan Qin¹ and Liang Wang¹, (1)Boston University, Boston, United States, (2)Georgia Institute of Technology, Daniel Guggenheim School of Aerospace Engineering, Atlanta, United States

Interpretable Machine Learning for ICME Identification: Leveraging Solar Wind Helium Abundance, Compressibility, and Cross Helicity (1937273)

Benjamin L. Alterman¹, Andreas Weiss¹, Fernando Carcaboso², Sanchita Pal¹, Dr. Yogesh ., PhD³, Brent M Randol⁴, Mihailo Martinovic⁵, Michael Louis Stevens⁶, Megha Mahendrabhai Pandya⁷, Bennett Maruca⁸, Leon Ofman¹, Lynn B Wilson III⁴, Li Chen⁹, Adam Szabo⁴, Teresa Nieves-Chinchilla¹⁰ and Christian Möstl¹¹, (1)NASA Goddard Space Flight Center, Greenbelt, United States, (2)NASA Goddard Space Flight Center, Heliophysics Science Division, Greenbelt, United States, (3)Indian Institute of Technology Gandhinagar, Gandhinagar, India, (4)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (5)University of Arizona, Lunar and Planetary Laboratory, Tucson, AZ, United States, (6)Smithsonian Astrophysical Observatory, Cambridge, MA, United States, (7)Catholic University of America, Washington, DC, United States, (8)Center for Astrophysics, Berkeley, CA, United States, (9)NASA GSFC, Greenbelt, United States, (10)NASA Goddard Space Flight Center, Heliophysics Science Division, MD, United States, (11)Austrian Academy of Sciences, Vienna, Austria

Investigating Tidal Effects in Earth's Plasmasphere Using a Machine Learning Model (1963377)

Jonathan Mellina, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States and Dr. Xiangning Chu, Laboratory for Atmospheric and Space Physics, Boulder, United States

Modeling Storm-Time Ionospheric Outflows Using FAST/TEAMS Observations and Machine Learning (1921287)

Taeho Lim, University of New Hampshire Main Campus, Space Science Center, Durham, United States, Lynn M Kistler, Univ New Hampshire, Durham, United States, Chris Mouikis, University of New Hampshire Main Campus, Physics, Durham, United States, Jing Liao, University of New Hampshire, Durham, United States and Niloufar Nowrouzi, Boston University, Center for Space Physics, Boston, United States

Noise Analysis of Geosynchronous Global-Scale Observations with AI method of the Limb and Disk (GOLD) Mission Far Ultra Violet (FUV) Image Data (1847920)

Jongkil Lee, Chungbuk National University, Cheongju, Korea, Republic of (South)

Predicting The Plasma Density In The Magnetosheath Using Machine Learning (1964261)

Zawad Islam, CUNY City College of New York, New York, United States, Bayane Michotte de Welle, NASA GSFC 673, Greenbelt, United States, M. Chantale Damas, CUNY Queensborough Community College, Bayside, United States and Hyunju KIM Connor, NASA Goddard Space Flight Center, Greenbelt, United States

Prediction of Global Ionospheric TEC in response to the Solar Flares (1883958)

Yang Pan, Zihan Wang and Mingwu Jin, University of Texas at Arlington, Arlington, United States

Real-Time Estimation of Cross Polar Cap Potential from IMEF: A Machine Learning Approach to Dayside Reconnection Diagnostics (1935942)

Alireza Motazedian, University of New Hampshire Main Campus, Durham, NH, United States, Matthew R Argall, University of New Hampshire, Durham, United States and Brianna Isola, University of New Hampshire Main Campus, Durham, United States

Reconstruction of two-dimensional magnetohydrodynamic and Hall magnetohydrodynamic equilibria in space using physics-informed neural networks (1871546)

Hiroshi Hasegawa¹, Eunjin Choi², Kyoung-Joo Hwang³ and Kyunghwan Dokgo³, (1)Institute of Space and Astronautical Science, JAXA, Sagamihara, Japan, (2)Southwest Research Institute, Space Science Division, San Antonio, United States, (3)Southwest Research Institute, San Antonio, United States

Revealing the global morphology of the magnetosphere during substorms by mining three decades of multi-mission space magnetic field data (Invited) (1924152)

Grant Killian Stephens¹, Mikhail I. Sitnov¹, Robert S Weigel² and Nikolai A Tsyganenko³, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)George Mason University, Fairfax, VA, United States, (3)Saint-Petersburg State University, Saint-Petersburg, Russia

Solar Wind Structure Decipher Clustering Using iSAX-pipeline Composed of iSAX Compression, and HDBSCAN (1986437)

Jasmine Kobayashi¹, Daniela Martin², Valmir Moraes Filho³, Jinsu Hong⁴, Connor O'Brien⁵, Andrés Muñoz-Jaramillo¹, Evangelia Samara^6,7 and Joseph Gallego⁸, (1)Southwest Research Institute Boulder, Boulder, CO, United States, (2)University of Delaware, Newark, DE, United States, (3)Catholic University of America, Washington, DC, United States, (4)Georgia State University, Atlanta, United States, (5)Boston University, Center for Space Physics, Boston, MA, United States, (6)NASA Goddard Space Flight Center, Heliophysics Science Division, Greenbelt, United States, (7)The Catholic University of America, Washington, DC, United States, (8)Drexel University, Computer and Information Science, Philadelphia, PA, United States

Substorm Prediction with LSTM: Key Solar Wind Drivers and a Comparative Study of SuperMAG Onset Lists as Reference Labels (1984987)

Purbi Adhya, Spring Hill College, Physics, Mobile, United States, Ruthba Yasmin, University of South Alabama, Electrical Engineering, Mobile, United States, Piyas Chowdhury, University of South Alabama, Mobile, AL, United States, Mohamed Shaban, University of South Alabama, Electrical and Computer Engineering, Mobile, United States and Edmund A Spencer, University of South Alabama, Electrical and Computer Engineering, Mobile, AL, United States

Summary of Efforts towards Operationalizing Physics-based Ionosphere-Thermosphere Models (Invited) (1893563)

Piyush Mehta, Anirudh Tapedia and Daniele Sicoli, West Virginia University, Morgantown, United States

Towards an Interpretable Machine Learning Model of Localized Geomagnetic Disturbances in Terms of Solar Wind Drivers (1892322)

Raman Mukundan, University of New Hampshire Main Campus, Durham, NH, United States, Amy M Keesee, University of New Hampshire, Physics and Space Science Center, Durham, United States, Michael Coughlan, NASA GSFC, Greenbelt, United States, Victor A Pinto, UCLA, Los Angeles, United States and Jose Paulo Marchezi, CRS/INPE - UFSM, Santa Maria, Brazil

Using Machine Learning Explainability Techniques to Examine Drivers of Ground Magnetic Field Localization (1873072)

Michael Coughlan¹, Amy M Keesee², Victor A Pinto^3,4, Raman Mukundan⁵, Jose Paulo Marchezi⁶, Mayowa Adewuyi⁷, Joel Tibbetts⁷, Jeremiah W Johnson⁸, Hyunju KIM Connor⁹ and Donald L Hampton¹⁰, (1)University of New Hampshire Main Campus, Durham, NH, United States, (2)University of New Hampshire, Physics and Space Science Center, Durham, United States, (3)Universidad de Santiago de Chile, Physics, Santiago, Chile, (4)University of Santiago Chile, Santiago, Chile, (5)University of New Hampshire, Department of Physics and Astronomy, Durham, United States, (6)CRS/INPE - UFSM, Santa Maria, Brazil, (7)University of New Hampshire Main Campus, Durham, United States, (8)University of New Hampshire, Applied Engineering and Sciences, Manchester, United States, (9)NASA Goddard Space Flight Center, Greenbelt, United States, (10)University of Alaska Fairbanks, Fairbanks, AK, United States

Utilizing Machine Learning to Predict High-Latitude Ionospheric Electrodynamics (1927187)

Jubyaid Uddin¹, Sai Gowtam Valluri², Hyunju KIM Connor², Yang He³ and M. Chantale Damas³, (1)CUNY The City College of New York, New York, United States, (2)NASA Goddard Space Flight Center, Greenbelt, United States, (3)CUNY Queensborough Community College, Bayside, United States

See more of: SPA-Magnetospheric Physics

<< Previous Session Proposal | Next Session Proposal >>

SM002 Artificial Intelligence (AI) for scientific discovery in Solar Wind-Earth Interaction

Session Description:

Index Terms:

SM002
Artificial Intelligence (AI) for scientific discovery in Solar Wind-Earth Interaction