SM005
Applications of Data Science and Engineering to Magnetospheric Physics and Aeronomy

Session ID#: 82875

Session Description:
Space science is a data-rich field, comprising data from many space- and ground-based instruments developed over the last several decades. This dataset is made up of numerous important parameters measured in the near Earth space environment and provide crucial information required to answer important questions in the field. However, working with such massive datasets comes with its own set of challenges, both in terms of data engineering and analysis. Recently there has been a remarkable advancement in the field of data science which can be attributed to better infrastructure and availability of many open source libraries. This session solicits contributions describing applications of data science and engineering, data mining, and machine learning to space science. We particularly welcome contributions focusing on applications of tools and techniques that provide real time analysis, assist scientific operation and discovery, or contribute to the advancement of science in general.
Index Terms:

1914 Data mining [INFORMATICS]
1942 Machine learning [INFORMATICS]
2447 Modeling and forecasting [IONOSPHERE]
2722 Forecasting [MAGNETOSPHERIC PHYSICS]

Primary Convener:  Bharat Kunduri, Virginia Polytechnic Institute and State University, Blacksburg, VA, United States
Conveners:  Maimaitirebike Maimaiti, Virginia Tech, Blacksburg, VA, United States, Asti Bhatt, SRI International, Menlo Park, CA, United States and Ashton Seth Reimer, University of Saskatchewan, Saskatoon, SK, Canada
Primary Liaison:  Bharat Kunduri, Virginia Tech, Blacksburg, VA, United States
 
Assimilative Mapping of Geospace Observations (AMGeO): Data Science Tools for Collaborative Geospace Systems Science (Invited) (507868)
Tomoko Matsuo1, Liam M Kilcommons1, J. Michael Ruohoniemi2 and Brian J Anderson3, (1)University of Colorado Boulder, Boulder, CO, United States, (2)Virginia Polytechnic Institute and State University, Blacksburg, VA, United States, (3)Johns Hopkins Univ, Laurel, MD, United States
 
Novel approaches to geospace particle transfer in the digital age: Progress through data science (513582)
Ryan Michael McGranaghan, Atmospheric and Space Technology Research Associates, LLC, Boulder, CO, United States, Enrico Camporeale, University of Colorado, Cooperative Institute for Research in Environmental Sciences, Boulder, United States, Kristina A Lynch, Dartmouth College, Hanover, NH, United States, Téo Bloch, University of Reading, Reading, United Kingdom, Spencer Hatch, University of Bergen, Bergen, Norway, Irina S Zhelavskaya, Organization Not Listed, Washington, DC, United States, Susan Skone, University of Calgary, Calgary, AB, Canada, Mathew James Owens, Uinversity of Reading, Reading, United Kingdom, Jesper W Gjerloev, Johns Hopkins University - Applied Physics Laboratory, Laurel, MD, United States, Binzheng Zhang, High Altitude Observatory, Boulder, CO, United States and Yuri Shprits, University of California Los Angeles, Los Angeles, United States
 
Modelling of SuperDARN Cross Polar Cap Potential by applying regression analysis and machine learning (552947)
Ke Li1, Erxiao Liu1,2, Hongqiao Hu3 and Jianjun Liu3, (1)Hangzhou Dianzi University, Hangzhou, China, (2)Virginia Polytechnic Institute and State University, Blacksburg, United States, (3)Polar Research Institute of China, Shanghai, China
 
Total Electron Content (TEC) map completion with a deep learning model: DCGAN with Poisson blending (557634)
Yang Pan, University of Texas at Arlington, Arlington, TX, United States, Mingwu Jin Sr, University of Texas Arlington, Arlington, United States, Yue Deng, University of Texas Arlington, Arlington, TX, United States, Zhou Chen, Nanchang University, Nanchang, China and Shunrong Zhang, MIT Haystack Observatory, Westford, MA, United States
 
Reconstructing the Plasmasphere Dynamics from Geomagnetic Indices Using Neural Networks (576780)
Irina S Zhelavskaya, Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences, Potsdam, Germany, Yuri Shprits, GFZ German Research Centre for Geosciences, Potsdam, Germany, Maria Spasojevic, Stanford University, Stanford, CA, United States and Nikita Aseev, University of California Los Angeles, Los Angeles, CA, United States
 
Building a magnetic reconnection signature from particle distributions using machine learning (580034)
Romain Dupuis, Katholieke Universiteit Leuven, Leuven, Belgium, Giovanni Lapenta, Katholieke Universiteit Leuven, Department of Mathematics, Leuven, Belgium and Jorge Amaya, KU Leuven, Leuven, Belgium
 
Magnetic Substorm Onset Prediction Using Deep Learning (582571)
Maimaitirebike Maimaiti1, Bharat Kunduri2, J. Michael Ruohoniemi1 and Joseph B. H. Baker2, (1)Virginia Polytechnic Institute and State University, Blacksburg, VA, United States, (2)Virginia Tech, Blacksburg, VA, United States
 
Evaluation of the Relative Importance of Storm Characteristics on the TEC Enhancements in the US Sector (609043)
Shantanab Debchoudhury, Disha Sardana and Gregory Duane Earle, Virginia Polytechnic Institute and State University, Blacksburg, VA, United States
 
Science Discovery Using Data Science (Invited) (617333)
Syed Irfan Azeem, ASTRA, LLC, United States
 
Machine Learning for Gravity Wave Identification (627953)
Wendy Hawley Carande1, James Craft2, Justin N Carstens3, Cora E Randall4, Jeffrey Allen France5, Lynn Harvey1, James M Russell III6 and Scott Martin Bailey7, (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)Virginia Polytechnic Institute and State University, Bradley Department of Electrical and Computer Engineering, Blacksburg, VA, United States, (4)Univ Colorado, Boulder, CO, United States, (5)University of Colorado at Boulder, Boulder, CO, United States, (6)Hampton University, Department of Atmospheric and Planetary Sciences, Hampton, VA, United States, (7)Virginia Polytechnic Institute and State University, Blacksburg, VA, United States
 
Using Modern Day Machine Learning Techniques for Detection of Sunlight Contamination in FEEPS Data (632222)
James Craft1, Wendy Hawley Carande1, Drew L. Turner2, Joseph F. Fennell3, Daniel N Baker4 and Barry Mauk5, (1)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (2)The Aerospace Corporation, Los Angeles, CA, United States, (3)University of Colorado at Boulder, LASP, Boulder, CO, United States, (4)University of Colorado, Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (5)The Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States
See more of: SPA-Magnetospheric Physics
<< Previous Session Proposal | Next Session Proposal >>