P41D:
Machine Learning in Planetary Science: Introductions and Applications I Posters


Submit an Abstract to this Session


Session ID#: 50013

Session Description:
Machine Learning (ML) is the subfield of computer science that gives "computers the ability to learn without being explicitly programmed." As increasingly large nonlinear datasets are acquired, autonomy and machine intelligence have to play a more critical role in the interpretation of data from planetary exploration missions. There is a need for frameworks that can rapidly and intelligently extract information from these datasets in a manner useful for scientific analysis. The community is starting to respond to this need by applying machine learning approaches on various levels. This session will present ways on introducing machine learning into your workflow and explore research that leverages machine learning methods to enhance our scientific understanding of planetary data, increasing the return of planetary exploration missions. This does include data analysis on ground as well as on board a spacecraft to increase autonomy and/or decrease data volume and novel approaches to mission timeline planning.
Primary Convener:  Klaus-Michael Aye, University of Colorado at Boulder, Laboratory for Atmosphere and Space Physics, Boulder, CO, United States
Conveners:  Jörn Helbert, DLR, Berlin, Germany, Mario D'Amore, German Aerospace Center DLR Berlin, Berlin, Germany and Hannah Rae Kerner, Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, United States
Primary Liaison:  Klaus-Michael Aye, University of Colorado at Boulder, Laboratory for Atmosphere and Space Physics, Boulder, CO, United States
Chairs:  Klaus-Michael Aye, University of California Los Angeles, Los Angeles, CA, United States, Jörn Helbert, DLR, Berlin, Germany and Hannah Rae Kerner, Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, United States
OSPA Liaison:  Klaus-Michael Aye, University of California Los Angeles, Los Angeles, CA, United States

Cross-Listed:
  • IN - Earth and Space Science Informatics
Index Terms:

1942 Machine learning [INFORMATICS]
5464 Remote sensing [PLANETARY SCIENCES: SOLID SURFACE PLANETS]
5799 General or miscellaneous [PLANETARY SCIENCES: FLUID PLANETS]
6299 General or miscellaneous [PLANETARY SCIENCES: SOLAR SYSTEM OBJECTS]

Abstracts Submitted to this Session:

Machine Learning Approach to Deconvolution of Mid-Infrared Telescope Spectra of Mercury: Supporting MERTIS onboard ESA/JAXA BepiColombo mission (422640)
Indhu Varatharajan1, Mario D'Amore1, Alessandro Maturilli2, Jörn Helbert3 and Harald Hiesinger4, (1)German Aerospace Center DLR Berlin, Berlin, Germany, (2)German Aerospace Center DLR, Berlin, Germany, (3)DLR, Berlin, Germany, (4)Westfälische Wilhelms-Universität Münster, Münster, Germany
Automated Mineral and Geochemical Classification From Spectroscopy Data using Machine Learning (369458)
Nicola Ferralis, Massachusetts Institute of Technology, Materials Science and Engineering, Cambridge, MA, United States and Roger E Summons, Massachusetts Institute of Technology, Cambridge, MA, United States
Automatic detection of the lunar boulders with deep learning (376397)
Tomokazu Sato1, Chikatoshi Honda1, Naru Hirata2, Hirohide Demura2, Yoshiaki Ishihara3, Hiroyuki Sato4, Mitsuo Yamamoto3, Hiroka Inoue3, Makiko Ohtake5 and Hisashi Otake4, (1)University of Aizu, Aizu-Wakamatsu, Japan, (2)The University of Aizu, Aizu-Wakamatsu, Japan, (3)Japan Aerospace Exploration Agency, Sagamihara, Japan, (4)Japan Aerospace Exploration Agency, Kanagawa, Japan, (5)Planetary Science Department, Kanagawa, Japan
Autonomous Mapping of Surface Features on Mars (411350)
Mark Wronkiewicz, Development Seed, Washington, DC, United States, Hannah Rae Kerner, Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, United States and Tanya Harrison, Planet, Federal, Washington, DC, United States
Automated detection of lunar rockfalls using a Faster Region-based Convolutional Neural Network (Invited) (422238)
Valentin Tertius Bickel1,2, Charis Lanaras3, Andrea Manconi4, Simon Loew4 and Urs Mall5, (1)University of Bern, Center for Space and Habitability, Bern, Switzerland, (2)ETH Zurich, Geological Institute, Zurich, Switzerland, (3)ETH Swiss Federal Institute of Technology Zurich, Photogrammetry and Remote Sensing, Zurich, Switzerland, (4)ETH Swiss Federal Institute of Technology Zurich, Engineering Geology, Zurich, Switzerland, (5)Max Planck Institute for Solar System Research, Planets and Comets, Goettingen, Germany
Identifying Geological Processes through High Dimension Clustering of Planetary Surface Features (434004)
Yue Zhao, Vrije Universiteit Amsterdam, Amsterdam, Netherlands, Matthieu Laneuville, Tokyo Institute of Technology, Earth Life Science Institute, Tokyo, Japan, Nicholas Guttenberg, Araya Brain Imaging, Tokyo, Japan and Wim Van Westrenen, VU University Amsterdam, Amsterdam, Netherlands
Lightweight CNN-based Real-time Phase Picker Embedded in Seismic Sensors (436898)
Lijun Zhu1, Chenyu Li2, Zefeng Li3, Zhigang Peng4 and James H. McClellan1, (1)Georgia Institute of Technology Main Campus, School of Electrical and Computer Engineering, Atlanta, GA, United States, (2)Georgia Institute of Technology Main Campus, Atlanta, GA, United States, (3)California Institute of Technology, Pasadena, CA, United States, (4)Georgia Institute of Technology, School of Earth and Atmospheric Sciences, Atlanta, United States
Cross-stratification, not cross-stratification: Deep learning applications to Earth and planetary sedimentology (439058)
Keaton Cheffer, Texas A&M, Department of Geology and Geophysics, College Station, TX, United States, Marion Nachon, University of Nantes, Nantes, France and Ryan C. Ewing, Texas A&M University College Station, Department of Geology & Geophysics, College Station, TX, United States
Martian Crater Identification Using Deep Learning (447609)
Christopher Lee, University of Toronto, Physics, Toronto, ON, Canada
Automatic Detection of Magnetospheric Regions around Saturn using Cassini Data (452270)
Kiley Yeakel1, Jon Duane Vandegriff1, Donald G Mitchell1, Douglas C Hamilton2, Caitriona Mary Jackman3, Peter A Delamere4 and Elias Roussos5, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)University of Maryland College Park, College Park, MD, United States, (3)University of Southampton, Southampton, United Kingdom, (4)University of Alaska Fairbanks, Geophysical Institute, Fairbanks, AK, United States, (5)Max Planck Institute for Solar System Research, Göttingen, Germany
DBSCAN Hyperparameter Tuning for the Planet Four Citizen Science Project (455581)
Ganna Portyankina1, Klaus-Michael Aye2, Megan Elizabeth Schwamb3, Candice J. Hansen4, Adam McMaster5, Grant R.M. Miller5, Brian Carstensen6, Christopher Snyder6, Michael Parrish6, Stuart Lynn6, Chuhong Mai7, David Miller6, Robert J. Simpson5 and Afron M. Smith6, (1)University of Colorado at Boulder, Boulder, United States, (2)Laboratory for Atmospheric and Space Physics, Boulder, CO, United States, (3)Organization Not Listed, Washington, DC, United States, (4)Planetary Science Institute, Tucson, United States, (5)Oxford Astrophysics, Oxford, United Kingdom, (6)Adler Planetarium, Chicago, United States, (7)School of Earth and Space Exploration, Arizona State University, Tempe, United States
NASA Frontier Development Lab: Applied Artificial Intelligence for Space Science and Exploration (Invited) (467545)
Anamaria Berea, University of Central Florida, Orlando, FL, United States

See more of: Planetary Sciences