IN11A:
Convergence in Space Physics and Earth Science: Discovery Through Machine Learning I


Submit an Abstract to this Session


Session ID#: 60513

Session Description:
Machine learning is increasingly used in a wide variety of scientific disciplines to advance knowledge in the age of big data and novel data analytics. However, application of machine learning algorithms to Earth and Space Science datasets is still in its infancy, and the question of how to incorporate uncertainties and physics knowledge remains unanswered. The common paradigm of applying machine learning to create new knowledge in both Space Physics and Earth Science provides a foundation to discuss their convergence. Besides being the pinnacle of evolutionary integration across disciplines, convergent research is now a central investment focus at both NASA and NSF. We invite contributions that exemplify the application of machine learning in Space Physics and Earth Sciences. The session will spark discussion of how machine learning methodology transfer may serve to bridge disciplines, leading to the opening of new research vistas and collaboration among researchers seeking future funding opportunities.
Primary Convener:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States
Conveners:  Justin Jay Hnilo, US Department of Energy, Washington, DC, United States, Kerstin Lehnert, Columbia University, Lamont-Doherty Earth Observatory, Palisades, United States and Renu Joseph, US Department of Energy, Germantown, MD, United States
Primary Liaison:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States
Chairs:  Ryan Michael McGranaghan, NASA Jet Propulsion Laboratory, Boulder, United States, Justin Jay Hnilo, U.S. Department of Energy, Germantown, MD, Washington, United States and Kerstin Lehnert, Columbia University, Lamont-Doherty Earth Observatory, Palisades, United States
OSPA Liaison:  Renu Joseph, US Department of Energy, Germantown, MD, United States
Co-Organized with:
Earth and Space Science Informatics, and SPA-Solar and Heliospheric Physics

Cross-Listed:
  • A - Atmospheric Sciences
  • NG - Nonlinear Geophysics
  • SA - SPA-Aeronomy
  • SH - SPA-Solar and Heliospheric Physics

Proposed Co-Organized Session with:
  • A - Atmospheric Sciences
  • NG - Nonlinear Geophysics
  • SA - SPA-Aeronomy
  • SH - SPA-Solar and Heliospheric Physics
Index Terms:

1906 Computational models, algorithms [INFORMATICS]
1914 Data mining [INFORMATICS]
1942 Machine learning [INFORMATICS]
1978 Software re-use [INFORMATICS]

Abstracts Submitted to this Session:

Towards Exascale Deep Learning for Climate Science (Invited) (348283)
Mr Prabhat1, Thorsten Kurth2, Sean Treichler3, Josh Romero3, Mayur Mudigonda1, Massimiliano Fatica4, Michael Houston3, Ankur Mahesh5, Karthik Kashinath6, Mike Matheson7, Mallikarjun Shankar8, Travis Allen O'Brien9, Michael F Wehner10 and William Drew Collins11, (1)University of California Berkeley, Berkeley, CA, United States, (2)NVIDIA Corporation, Zurich, Switzerland, (3)NVIDIA, Santa Clara, United States, (4)Organization Not Listed, Washington, DC, United States, (5)Lawrence Berkeley National Laboratory, Earth and Environmental Science, Berkeley, United States, (6)NVIDIA Corporation, Santa Clara, CA, United States, (7)OLCF, Oak Ridge, TN, United States, (8)Seattle, WA, United States, (9)Lawrence Berkeley National Lab, Climate & Ecosystem Sciences Division, Berkeley, United States, (10)Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, United States, (11)Berkeley Lab and UC Berkeley, Berkeley, United States
Convergence Challenges the Culture of Science (Invited) (350448)
Michael M Little, NASA Headquarters, Washington, DC, United States
Atmospheric Fronts in Climate Models: Inter-comparison Across Historical and Future Scenarios (413826)
James Clark Biard, North Carolina State University, North Carolina Institute for Climate Studies, Asheville, NC, United States and Kenneth Kunkel, North Carolina State University, Asheville, United States
NEX-AI: A Cloud and HPC Agnostic Framework for Scaling Deep Learning and Machine Learning Applications for Earth Science (429782)
Sangram Ganguly1, Subodh Kalia2, Kate Duffy3, Edward Durham Collier4, Geri Elise Madanguit2, Gayaka Shreekant5, Shuang Li1, Supratik Mukhopadhyay4, Mr. Prabhat6, Thomas Vandal7, Adrian Toni Albert8, Hirofumi Hashimoto1, Weile Wang9, Tsengdar J Lee10, Diptanu Gon Choudhury11, Andrew Michaelis1, Sassan Saatchi12, Compton J Tucker13 and Ramakrishna R Nemani1, (1)NASA Ames Research Center, Moffett Field, CA, United States, (2)BAER Institute, Mountain View, CA, United States, (3)Zeus AI, Cambridge, United States, (4)Louisiana State University, Computer Science, Baton Rouge, LA, United States, (5)BAER Institute, Mountainview, CA, United States, (6)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (7)Northeastern University, Boston, MA, United States, (8)Massachusetts Institute of Technology, Cambridge, MA, United States, (9)NASA/AMES Research Center, Moffett Field, United States, (10)NASA, Washington, United States, (11)Facebook Inc, Palo Alto, United States, (12)NASA Jet Propulsion Laboratory, Pasadena, United States, (13)NASA Goddard Space Flight Center, Earth Science Division, Greenbelt, MD, United States
Advancing Knowledge through Machine Learning: Examples from the National Science Foundation (Invited) (440591)
Amy L Walton, National Science Foundation, Arlington, VA, United States
Modern Machine Learning for Space Weather Forecasts (445950)
Wendy Hawley Carande1, James Craft2, Andrew R Jones3, Tracey Morland4, Kim Kokkonen1, Justin Cai1, Laura Sandoval1 and Maxine Hartnett1, (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
Automated Machine Learning as a Service for the Earth Sciences (458711)
Brian D Wilson1, Sujen Shah2, Chris A Mattmann3, Giuseppe Totaro4, Mark K Hoffmann5, Vishal Lall5, Srinidhi Nandakumar6, Wayne Burke7, Paul Ramirez7 and Ryan Michael McGranaghan8, (1)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, United States, (2)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (3)NASA Jet Propulsion Laboratory, Pasadena, CA, United States, (4)Sapienza University of Rome, Rome, Italy, (5)NASA Jet Propulsion Laboratory, Pasadena, United States, (6)University of Southern California, Los Angeles, United States, (7)Jet Propulsion Laboratory, Pasadena, CA, United States, (8)Atmospheric and Space Technology Research Associates, LLC, Louisville, CO, United States
Cray Converged System Architecture and Software for Machine Learning and Data Analytics at Extreme Scale (466249)
Ilene Carpenter, Cray Inc, Arvada, CO, United States, Arti Garg, Cray Inc., Artificial Intelligence, San Jose, CA, United States and Benjamin Robins, Cray Inc., Software Engineering, Seattle, WA, United States

See more of: Earth and Space Science Informatics