The deadline to submit a session, town hall, or pre-conference workshop proposal for AGU25 has passed. Please search for and review proposed sessions below. Please note this site is frozen as of 4/29/25 and will not reflect any changes to proposals made after this date.


Conveners will be contacted by the AGU25 Program Committee with any requests for mergers or edits to proposals. Conveners will be notified of the acceptance of their proposal in mid-June.


Abstract submissions will also open in mid-June and the deadline for abstract submissions is 30 July, 2025.


Please visit the AGU25 website for more information or please contact AGU with any questions.

Session Proposal: Machine Learning and Data Science Methods for Planetary Science (AGU25)

P023
Machine Learning and Data Science Methods for Planetary Science

Session ID#: 249660

Session Description:
Many facets of research in planetary science rely on analyzing large volumes of in-situ and remote spacecraft data. Traditionally, these data were collected and analyzed manually. In recent decades, developments in machine learning (ML) techniques have begun to gradually augment traditional methods, answering the need for automation that can efficiently and intelligently extract information from large datasets in a useful manner.This session will be dedicated to data driven research that leverages ML and data science to enhance our scientific understanding and return from planetary data and missions. Topics may encompass studies from Earth-based data and existing and future planetary missions. Submissions are welcome for applications across science and engineering, including but not limited to: spacecraft operations and mission planning; surface, atmosphere, and space environment; object detection and classification; change detection; ML augmented physics-based models; interpretable methods; and other studies that apply ML and data science methods to planetary science.
Co-Sponsor(s):
  • EP - Earth and Planetary Surface Processes
  • SY - Science and Society
  • SH - SPA-Solar and Heliospheric Physics
  • SM - SPA-Magnetospheric Physics
Index Terms:

1906 Computational models, algorithms [INFORMATICS]
1916 Data and information discovery [INFORMATICS]
1942 Machine learning [INFORMATICS]
6297 Instruments and techniques [PLANETARY SCIENCES: SOLAR SYSTEM OBJECTS]
Primary Convener:  Ramanakumar Sankar, University of California Berkeley, Berkeley, CA, United States
Conveners:  Abigail Azari, University of Alberta, Alberta Machine Intelligence Institute, Edmonton, Canada, Hannah Rae Kerner, Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, United States and Lior Rubanenko, Tel Aviv University, Earth and Planetary Science, Tel Aviv, Israel; Planetary Science Institute Tucson, Tucson, United States
Student/Early Career Convener:  Ramanakumar Sankar, University of California Berkeley, Berkeley, CA, United States
 
Detection of Pitted Mounds on Mars (Isidis Planitia) Using Faster R-CNN (1869405)
Precious Batubo, University of Louisiana at Lafayette, Lafayette, United States, Gabriele Morra, University of Louisiana at Lafayette, Lafayette, LA, United States, Davide Oppo, University of Louisiana at Lafayette, School of Geosciences, Lafayette, LA, United States, Chris H Okubo, U.S. Geological Survey, Astrogeology Science Center, Flagstaff, United States and Colin M Dundas, U. S. Geological Survey, Flagstaff, AZ, United States
 
Efficient Content-Based Image Retrieval with User Feedback for Mars Geological Studies through Vision Transformer (1876650)
Jichao Fang, Northern Illinois University, DeKalb, IL, United States and Wei Luo, Northern Illinois Univeristy, DeKalb, United States
 
Deep Reinforcement Learning for Rapid Spacecraft Science Operations Scheduling to Maximize Science Return (1880520)
Alex Zhang, University of Illinois at Urbana-Champaign, Electrical and Computer Engineering, Urbana, United States and Lara Waldrop, University of Illinois at Urbana-Champaign, Electrical and Computer Engineering, Urbana, IL, United States
 
Exploring Deep Learning Solutions for Photometric Calibration of JunoCam and Enhanced Navigation for Mars Science Helicopter (Invited) (1882971)
Georgios Georgakis, Jet Propulsion Laboratory, California Institute of Technology, Sylmar, California, UNITED STATES
 
Black Hole Detection Through Gravitational Microlensing (1887333)
Liza Friedman1, Juan Sanchez2, Zoe Kramer2, Olivia Vanicor2, Roshan Ladha2, Krishnanujam Srinivas3, Rohan Ravula2 and Anjali Kazmierczak2, (1)NASA SEES STEM Enhancement in Earth Science program, Austin, TX, UNITED STATES, (2)NASA SEES STEM Enhancement in Earth Science program, Austin, United States, (3)NASA SEES STEM Enhacement in Earth Science program, Austin, United States
 
Derivation of dust optical depth from images taken by a Mars rover using a radiative transfer model and deep learning (1888898)
Itsuki Kashimura1, Takeshi Kuroda1, Tomohiro Sato2, Hironobu Iwabuchi1 and Naoki Terada1, (1)Tohoku University, Department of Geophysics, Graduate School of Science, Sendai, Japan, (2)NICT National Institute of Information and Communications Technology, Tokyo, Japan
 
Deep Learning to Assess the Effective Resolution of LROC NAC DTMs (1899661)
Steven Nystrom, Madeleine Manheim, Megan Henriksen and Mark Southwick Robinson, Intuitive Machines, Phoenix, United States
 
Unifying Pyrolysis-Gas Chromatography-Mass Spectrometry Data for Agnostic Biosignature Detection with Peak Alignment and Vector Embeddings (1903426)
Miles Walters1,2, Emily Dobberfuhl3, Anirudh Prabhu4, George D Cody4, Grethe Hystad5, H. James Cleaves II6, Robert Hazen4 and Michael L Wong4, (1)Carnegie Science, Washington, D.C., United States, (2)Bullis High School, Potomac, United States, (3)University of Wisconsin Madison, Madison, WI, United States, (4)Carnegie Institution for Science, Earth and Planets Laboratory, Washington, United States, (5)Purdue University Northwest, Department of Mathematics and Statistics, Hammond, United States, (6)Tokyo Institute of Technology, Earth-Life Science Institute (ELSI), Tokyo, Japan
 
Downstream Science Applications and Benchmark Development for Lunar Science Foundation Models (1929889)
Andrew Annex1,2, Michael K. Barker3, Zachary Morse4,5, Vishnu Viswanathan3,6, Sujit Roy7,8, Daniela Szwarcman9, Vishal Gaur10, Gabrielle Nyirjesy11, Ankur Kumar10, Rachel Slank12, Paolo Fraccaro13, Himanshu Patil10, Campbell Watson14, Juan Bernabe-Moreno15 and Rahul Ramachandran7, (1)SETI Institute, Carl Sagan Center for Research, Mountain View, United States, (2)NASA Ames Research Center, Planetary Systems Branch (STT), Moffett Field, United States, (3)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (4)NASA Goddard Space Flight Center, Greenbelt, United States, (5)Howard University, Washington, United States, (6)University of Maryland Baltimore County, Baltimore, MD, United States, (7)NASA Marshall Space Flight Center, Huntsville, United States, (8)University of Alabama in Huntsville, Huntsville, AL, United States, (9)IBM Research, Rio de Janeiro, Brazil, (10)University of Alabama in Huntsville, Huntsville, United States, (11)IBM Research USA, Yorktown Heights, NY, United States, (12)Universities Space Research Association Huntsville, Huntsville, United States, (13)IBM Research, Daresbury, United Kingdom, (14)IBM Research, Yorktown Heights, United States, (15)IBM Research, Mulhuddart, Ireland
 
Using Machine Learning to Determine Asteroid Mineralogies (1932667)
Thomas Burbine, Mount Holyoke College, Physics & Astronomy, South Hadley, United States, Sulagna Saha, Mount Holyoke College, Computer Science, South Hadley, United States, Tanish Parida, Acton-Boxborough Regional High School, Acton, United States and Melinda Darby Dyar, Planetary Science Institute, Tucson, United States
 
Learning the mechanical behavior of Martian Regolith via generative physical AI (1936275)
Xuhai Tang, Jiangmei Qiao, Shengzong Xu and Fei Gao, Wuhan University, School of Civil Engineering, Wuhan, China
 
Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks (1939981)
Mirali Purohit1, Bimal Gajera2, Vatsal Malaviya2, Irish Mehta2, Kunal Kasodekar2, Jacob B Adler3, Steven Lu4, Umaa Rebbapragada5 and Hannah Rae Kerner6, (1)Arizona State University, Tempe, AZ, United States, (2)Arizona State University (ASU), Tempe, United States, (3)Arizona State University, School of Computing and Augmented Intelligence, Tempe, United States, (4)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (5)Jet Propulsion Laboratory, California Institute of Technology, Machine Learning and Instrument Autonomy, Pasadena, United States, (6)Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, United States
 
Enhancing Mission Operations and Science Return with Machine Learning (Invited) (1945821)
Valentin Tertius Bickel, University of Bern, Center for Space and Habitability, Bern, Switzerland
 
Automated Mapping of Wrinkle Ridge Faults on Venus using Machine Learning (1955686)
Evan Chou1,2, Luis Hernandez3, Zaki Hasnain4, Suzanne Smrekar4, Linn Thuya5,6, Justin House7, Shiori Nakaya8 and Sylvia Mendoza5, (1)Pasadena City College, Department of Natural Sciences, Pasadena, United States, (2)University of California San Diego, Electrical and Computer Engineering Department, La Jolla, CA, United States, (3)Fayetteville State University, Department of Mathematics and Computer Science, Fayetteville, United States, (4)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (5)Pasadena City College, Los Angeles, United States, (6)University of California Los Angeles, Los Angeles, United States, (7)Fayetteville State University, Intelligent Systems Laboratory, Fayetteville, United States, (8)University of California Riverside, Earth and Planetary Sciences, Riverside, United States
 
Mapping Wrinkle Ridges on Venus with Machine Learning: Training Data Integrity and Model Evaluation (1962563)
Sylvia Mendoza1, Suzanne E Smrekar2, Zaki Hasnain3, Shiori Nakaya4, Evan Chou5 and Linn Thuya1, (1)Pasadena City College, Los Angeles, United States, (2)JPL/NASA/Caltech, Pasadena, United States, (3)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (4)University of California Riverside, Earth and Planetary Sciences, Riverside, United States, (5)University of California San Diego, Electrical and Computer Engineering Department, La Jolla, CA, United States
 
From Tiles to Tectonics: Stitching ML-Segmented Faults into a Global Venus Fault Map (1965844)
Linn Thuya1,2, Luis Hernandez3, Justin House4, Zaki Hasnain5, Sylvia Mendoza1, Evan Chou6,7 and Suzanne E Smrekar8, (1)Pasadena City College, Los Angeles, United States, (2)University of California Los Angeles, Los Angeles, United States, (3)Fayetteville State University, Department of Mathematics and Computer Science, Fayetteville, United States, (4)Fayetteville State University, Intelligent Systems Laboratory, Fayetteville, United States, (5)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (6)Pasadena City College, Department of Natural Sciences, Pasadena, United States, (7)University of California San Diego, La Jolla, CA, United States, (8)JPL/NASA/Caltech, Pasadena, United States
 
Lava Flow Composition Discriminant Analysis using Training Data Sets on Earth and its Potential for Classification of Lava Flows on Planetary Bodies (1975721)
Logan McQueen, Lake Superior State University, School of Chemistry, Environmental, and Geological Sciences, Sault Saint Marie, United States, Pradeep N Ranasinghage, Lake Superior State University, School of Chemistry, Environment, and Geological Sciences, Sault Sainte Marie, United States, Paul Robert Kelso, Lake Superior State University, School of Chemistry, Environmental, and Geosciences, Sault Sainte Marie, United States and Nicholas Gordon, Lake Superior State University, College of Arts and Sciences, Sault Sainte Marie, United States
 
Enhanced Detection of Martian Dust Devils from Rover Images using Machine Learning (1976421)
Kacy Hatfield, Arizona State University, Tempe, AZ, United States; NASA Goddard Space Flight Center, Greenbelt, United States, Conor A Nixon, NASA Goddard Space Flight Center, Planetary Systems Laboratory, Greenbelt, MD, United States and John Santerre, University of California Berkeley, School of Information, Berkeley, United States
 
Can Earth’s AI Predict Martian Weather? A Foundation Model Perspective (1977033)
Jian Li1, Mark Carroll2, Geronimo Villanueva3 and Scott D. Guzewich3, (1)NASA Goddard Space Flight Center, Data Science Group, Greenbelt, MD, United States, (2)NASA Goddard Space Flight Center, Data Science Group, Greenbelt, United States, (3)NASA Goddard Space Flight Center, Greenbelt, United States
 
Grain-Scale Morphometrics of Martian Sedimentary Deposits via Neural Network Segmentation of Rover Imagery (1982723)
Ayden Hayes1, Ari Koeppel1, Emma Rogers1, Mansa Krishna1 and Shreya Gandhi2, (1)Dartmouth College, Department of Earth Sciences, Hanover, United States, (2)Dartmouth College, Hanover, NH, United States
 
Data-Driven Modeling of the Martian Induced Magnetosphere Using Physics-Informed Neural Networks (1991843)
Jiawei Gao1, Chuanfei Dong2, Liang Wang2 and Yilan Qin2, (1)Boston University, Center for Space Physics and Department of Astronomy, Boston, United States, (2)Boston University, Boston, United States
 
Semi-Automated Fragmentation Modeling for Jovian Impacts (1995954)
Kathryn Davis, Florida Institute of Technology, APSS, Melbourne, FL, United States, Ramanakumar Sankar, University of California Berkeley, Berkeley, CA, United States and Csaba J Palotai, Florida Institute of Technology, APSS, Melbourne, United States
 
Characterizing the Color and Structure of Jupiter’s Clouds and Aerosols with Deep Learning (2001585)
Emma Dahl1, Ramanakumar Sankar2, Bernadette Bucher3, Aditya Singh3, Shrey Shah3, G. Eichstädt4, Michael Wong5 and Georgios Georgakis6, (1)California Institute of Technology, Pasadena, CA, United States, (2)Florida Institute of Technology, Melbourne, United States, (3)University of Michigan, Ann Arbor, United States, (4)Independent scholar, Stuttgart, Germany, (5)Space Sciences Laboratory, Berkeley, United States, (6)Jet Propulsion Laboratory, California Institute of Technology, Sylmar, California, UNITED STATES
 
Efficient Uncertainty Quantification for Iterative Retrieval of Exospheric Density (2004528)
Evan Widloski, University of Illinois at Urbana-Champaign, Maryville, TN, UNITED STATES and Lara Waldrop, University of Illinois at Urbana-Champaign, Electrical and Computer Engineering, Urbana, IL, United States
See more of: Planetary Sciences
<< Previous Session Proposal | Next Session Proposal >>