C024
Machine Learning in the Cryosphere
Session ID#: 247072
Session Description:
Applications of machine learning tools in the cryosphere are rapidly evolving, influencing many facets of cryospheric science and transforming our ability to observe, model, and understand the Earth system. In this session, we invite submissions showcasing the use and applications of machine learning as applied to the cryosphere, including sea ice, land ice, snow, permafrost, ice sheets, ice shelves and more. We encourage submissions across a broad spectrum of applications, including - but not limited to - remote sensing, emulation of physical models, physics-informed machine learning, causal inference, calibration/initialization, uncertainty quantification, automated learning of processes, and the compilation of novel datasets. Examples of methodologies include classical statistical modelling, modern Bayesian inference frameworks, deep neural networks, or other frameworks that bring data-driven inference to bear on pressing problems in cryospheric science.
Index Terms:
0758 Remote sensing [CRYOSPHERE]
0776 Glaciology [CRYOSPHERE]
0798 Modeling [CRYOSPHERE]
Primary Convener: Ching-Yao Lai, Stanford University, Department of Geophysics, Stanford, United States
Conveners: Gong Cheng, Dartmouth College, Department of Earth Sciences, Hanover, NH, United States, Douglas Brinkerhoff, University of Montana, Department of Computer Science, Missoula, United States and Mauro Perego, Sandia National Laboratories, Albuquerque, United States
Leveraging GPU-based Computing and Physics-informed Deep Learning in IGM to Achieve High-resolution, Data-consistent Modelling of the Alps’ Last Glaciation Coupled with Particle Tracking (Invited) (1855026)
Tancrede Leger1, Guillaume Jouvet2, Sarah Kamleitner1, Jürgen Mey3, Andreas Vieli4, Samuel Urs Nussbaumer5, Brandon Finley1, Maxime Bernard1, Balthazar Allegri1, Susan Ivy-Ochs6, Andreas Henz4 and Frederic Herman1, (1)University of Lausanne, Lausanne, Switzerland, (2)University of Lausanne, Institute of Earth Surface Dynamics, Lausanne, Switzerland, (3)University of Potsdam, Potsdam, Germany, (4)University of Zurich, Zurich, Switzerland, (5)University of Zurich, Bern, Switzerland, (6)ETH Zurich, Zurich, Switzerland
DMFS: Differentiable Modeling for Forzen Soil Thermodynamic Characteristics (1859379)
Lingyun Gou1,2, Yuhao Ren3, Ming Xiao2, Zhen Liu3 and Chaopeng Shen2, (1)University of Wisconsin Madison, Department of Civil and Environmental Engineering, Madison, WI, United States, (2)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, (3)Department of Civil and Environmental Engineering, University of Virginia, Charlottesville, United States
Timeseries Classification of Greenland Ice Sheet Supraglacial Lake Evolution and Dynamics (Invited) (1863725)
Devon R Dunmire1, Aneesh Subramanian2, Alison F Banwell3, Emam Hossain4, Md Osman Gani4, Hammad Younas5 and Brendan Myers6, (1)University of Colorado Boulder, Department of Atmospheric and Oceanic Sciences, Boulder, United States, (2)University of Colorado Boulder, Atmospheric and Oceanic Sciences, La Jolla, United States, (3)Cooperative Institute for Research in Environmental Sciences, Boulder, United States, (4)University of Maryland Baltimore County, Department of Information Systems, Baltimore, United States, (5)Rice University, Houston, United States, (6)University of Colorado at Boulder, Department of Atmospheric and Oceanic Sciences, Boulder, United States
Using Thermal Model Ensemble and Machine Learning to Predict the Basal Temperature of the Northern Greenland Ice Sheet (1865972)
Leo Liu1, Donglai Yang2, Winnie Chu2 and Joseph A MacGregor3, (1)Emory University, Atlanta, GA, United States, (2)Georgia Institute of Technology Main Campus, Atlanta, United States, (3)NASA Goddard Space Flight Center, Greenbelt, United States
GEOCLASS-image, a Modular Cyberinfrastructure to Facilitate and Advance Machine Learning and Scene Classification in the Geosciences (1880344)
Silas Twickler, University of Colorado Boulder, Geomathematics, Remote Sensing and Cryospheric Sciences Laboratory; Electrical, Computer and Energy Engineering, Boulder, United States, Ute Herzfeld, University Colorado Boulder, Geomathematics, Remote Sensing and Cryospheric Sciences Laboratory; Electrical, Computer and Energy Engineering, Boulder, United States and Dr. Thomas Trantow, PhD, University of Colorado at Boulder, Geomathematics, Remote Sensing and Cryospheric Sciences Laboratory; Electrical, Computer and Energy Engineering, Boulder, United States
Long-Term Terminus Prediction Using Interpretable Machine Learning (1880580)
Kevin Shionalyn, University of Texas at Austin, Austin, TX, United States, Ginny Catania, University of Texas at Austin, Austin, United States, Daniel T Trugman, Los Alamos National Laboratory, Los Alamos, United States, Michael G Shahin, University of Kansas, Department of Geology, Lawrence, United States, Leigh A Stearns, University of Pennsylvania, Department of Earth and Environmental Sciences, Philadelphia, PA, United States and Denis Felikson, NASA Goddard Space Flight Center, Cryospheric Sciences Laboratory, Greenbelt, United States
TanDEM-X Penetration Bias Estimation by AI Algorithms in Antarctica using ICESat-2 and ECMWF Data (1885427)
Ankita Vashishtha1, Pietro Milillo2, Alexandre Becker Campos3, Paola Rizzoli3, Johan Nilsson4 and Jose Louis Nueso-Bello3, (1)University of Houston, Department of Civil and Environmental Engineering, Houston, United States, (2)University of Houston, Department of Civil and Environmental Engineering, Houston, TX, United States, (3)German Aerospace Centre DLR, Microwaves and Radar Institute, Munich, Germany, (4)Uppsala University, Department of Earth Sciences, Uppsala, Sweden
How Much and How Uniquely Can Neural Operators Recover Greenland Ice Mass Change from Sea Level Fingerprints? (1886045)
Xiyuan Bao1, Sophie Coulson2, Natasha Valencic3, Jerry X Mitrovica3, Sönke Dangendorf4, S. Mostafa Mousavi3 and Andrew Lloyd5, (1)Harvard University, Department of Earth and Planetary Sciences, Cambridge, MA, United States, (2)University of New Hampshire, Durham, United States, (3)Harvard University, Department of Earth and Planetary Sciences, Cambridge, United States, (4)Tulane University, Department of River-Coastal Science & Engineering, New Orleans, United States, (5)Columbia University, Lamont-Doherty Earth Observatory, New York, United States
Emulating surface melt over the Greenland ice sheet with ML tools: the MAR-IA model (1911498)
Marco Tedesco, Lamont Doherty Earth Observatory, Columbia University, Palisades, United States, Racheet Matai, Lamont -Doherty Earth Observatory, Palisades, United States and Xavier Fettweis, University of Liège, Département de Géographie, Liège, Belgium
Using physics-informed neural networks to constrain ice viscosity from ice-penetrating radar data (1914356)
George J Lu1, Yongji Wang2, Kavi Gollamudi3, Ching-Yao Lai4 and Jonathan Kingslake1, (1)Lamont-Doherty Earth Observatory, Palisades, United States, (2)New York University, Department of Mathematics, New York, United States, (3)University of California Santa Barbara, Santa Barbara, United States, (4)Stanford University, Department of Geophysics, Stanford, United States
Machine Learning Based Uncertainty Quantification for Ice Sheet Basal Friction Inversion (1927208)
Sinan He, Stanford University, Stanford, CA, United States, Ching-Yao Lai, Stanford University, Department of Geophysics, Stanford, United States, Facundo Sapienza, University of California Berkeley, Statistics, Berkeley, United States and Mauro Perego, Sandia National Laboratories, Albuquerque, United States
Identifying the current inland elevation limit of crevassing on Narsap Sermia, southwestern Greenland using machine learning (1927734)
Naureen Khan, University at Buffalo, Department of Geology, Buffalo, NY, United States and Kristin Poinar, University at Buffalo, Department of Earth Science, Buffalo, United States
Deep learning the flow law of Antarctic ice shelves (Invited) (1953473)
Yongji Wang, New York University, Department of Mathematics, New York, United States, Ching-Yao Lai, Stanford University, Department of Geophysics, Stanford, United States, David John Prior, University of Otago, Geology, Dunedin, New Zealand and Charlie Cowen-Breen, Massachusetts Institute of Technology, Mathematics, Cambridge, United States
Machine Learning Emulation of a Hyper-resolution Physical Snow Model to Assess Landscape-scale Forest Management Outcomes (1960759)
Dr. Joel A Biederman, PhD1, Ravindra Dwivedi2, Patrick D Broxton3, Travis Woolley4, Jackson Leonard5, Jessie K. Pearl6, Bohumil Svoma7, Charles Devine8 and Marcos Robles4, (1)Southwest Watershed Research Center, Tucson, AZ, United States, (2)University of Arizona, School of Natural Resources and the Environment, Tucson, United States, (3)University of Arizona, School of Natural Resources and the Environment, Tucson, AZ, United States, (4)The Nature Conservancy, Center for Science and Public Policy, Tucson, AZ, United States, (5)USDA Forest Service, Rocky Mountain Research Station, Flagstaff, AZ, United States, (6)The Nature Conservancy, Tucson, United States, (7)Salt River Project, Tempe, United States, (8)University of Arizona, Tucson, AZ, United States
A Machine-Learning Framework for Mapping Little Ice Age Maximum Glacial Extents (1981194)
Mohammad Salmani1, Beata M Csatho2, Jason P Briner1, Hui Gao1, Ana Carolina Moraes Luzardi1, Sophie Nowicki1 and Ivan Parmuzin1, (1)University at Buffalo, Department of Earth Sciences, Buffalo, United States, (2)University at Buffalo, Department of Earth Sciences, Buffalo, NY, United States
Evaluating Multiple AI/ML Models with Parallelized Jupyter Notebook Deployment in Kubernetes for Accelerated Arctic Geospatial Preprocessing and Predictive Visualization (1985327)
Meisam Shayeghmoradi1, Kyle Foerster2, Naima Kaabouch2, Sheridan Parker2 and Timothy Pasch3, (1)University of North Dakota, Grand Forks, ND, United States, (2)University of North Dakota, Grand Forks, United States, (3)The University of North Dakota, Department of Communication, Grand Forks, United States
MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater (2000893)
Björn Lütjens, IBM Research, Yorktown Heights, United States, Patrick Alexander, Columbia University, Lamont-Doherty Earth Observatory, New York, United States, Raf Antwerpen, ESRI, Redlands, United States, Til Widmann, Ai.Fish, Barcelona, Spain, Guido Cervone, Pennsylvania State University Main Campus, Department of Geography and Institute for Computational and Data Sciences, University Park, PA, United States and Marco Tedesco, Columbia University, Lamont-Doherty Earth Observatory, Palisades, NY, United States
