C001
A Data-driven Cryosphere: Insights from Machine Learning and Other Statistical Methods

Session ID#: 157890

Session Description:
As rich observations of the Earth become available, recent advances in data science play an important role in understanding the cryosphere and its interaction with the climate and other Earth systems. New studies have used in-situ or remotely sensed data to build or validate novel statistical algorithms for various tasks including but not limited to data classification, image segmentation, physics-based learning, solving inverse problems, and designing surrogate models. This session brings together a new understanding of the cryospheric physics empowered by rich data and these data-driven methods. We invite submissions from all subfields of cryospheric science with either of the following highlights: (1) machine learning or other data science methodology designed for or applied to cryospheric studies; and (2) scientific discovery made possible by using these novel methods.
Index Terms:

0799 General or miscellaneous [CRYOSPHERE]
1942 Machine learning [INFORMATICS]

Primary Convener:  Whyjay Zheng, University of California Berkeley, Statistics, Berkeley, CA, United States
Conveners:  Jordi Bolibar, Utrecht University, Institute for Marine and Atmospheric Research, Utrecht, Netherlands, Tasha Snow, Colorado School of Mines, Geophysics, Golden, CO, United States and Yara Mohajerani, EnvAI Solutions Inc., Toronto, Canada; University of Washington, Civil and Environmental Engineering, Seattle, United States
Student/Early Career Convener:  Facundo Sapienza, University of California, Berkeley, Statistics, Berkeley, United States
 
A Deep-learning-based Framework for Locating Retrogressive Thaw Slumps over the Permafrost Regions on the Qinghai-Tibetan Plateau (1140658)
Xia Zhuoxuan1, Lingcao Huang2, Lin Liu1, Chengyan Fan3, Jing Luo4, Cuicui Mu3 and Xiaoqing Peng3, (1)The Chinese University of Hong Kong, Earth System Science Programme, Hong Kong, China, (2)University of Colorado Boulder, Cooperative Institute for Research in Environmental Sciences, Boulder, United States, (3)Lanzhou University, College of Earth and Environmental Sciences, Lanzhou, China, (4)Chinese Academy of Sciences, Northwest Institute of Eco-Environment and Resources, Lanzhou, China
 
A Machine Learning Framework for Active and Passive Microwave Observation from Snow Water Equivalent Synthetic Aperture Radar And Radiometer (SWESARR) for Snow Depth Estimation. (1127745)
Evi Ofekeze1, Hans-Peter Marshall2, Jodi Mead1 and Ibrahim Olalekan Alabi1, (1)Boise State University, Boise, ID, United States, (2)Boise State University, Department of Geosciences, Boise, ID, United States
 
A Semi-Automatic Method for Predicting Subglacial Dry-Wet Distribution Based on Radio-Echo Sounding Data (1048435)
Mingzhu Yang1, Shinan Lang1, Xiangbin Cui2, Yiheng Cai1, Lin Li2, Xiaojun Liu3, Jingxue Guo2, Sun Bo2 and Martin J Siegert4, (1)Beijing University of Technology, Beijing, China, (2)Polar Research Institute of China, Shanghai, China, (3)Institute of Electronics, Chinese Academy of Sciences, Beijing, China, (4)Imperial College London, London, United Kingdom
 
Arctic sea ice prediction using ensemble deep learning models (1060757)
Junhwa Chi, Korea Polar Research Institute, Incheon, Korea, Republic of (South), Jihyun Bae, Sejong University, Seoul, South Korea and Young-Joo Kwon, Korea Polar Research Institute, Incheon, South Korea
 
Automated detection and tracking of small icebergs in the Amundsen Sea using Google Earth Engine (1094864)
YoungHyun Koo1, Hongjie Xie1, Hazem Mahmoud2 and Jurdana Masuma Iqrah3, (1)University of Texas at San Antonio, Department of Earth and Planetary Sciences, San Antonio, United States, (2)University of Texas at San Antonio, Department of Earth and Planetary Sciences, San Antonio, TX, United States, (3)University of Texas at San Antonio, Department of Computer Science, San Antonio, United States
 
Automated Detection of West Antarctic Persistent Polynas using Physics-Featurized Neural Networks (1154779)
Ellianna Abrahams, University of California Berkeley, Statistics, Berkeley, CA, United States, Tasha Snow, Colorado School of Mines, Geophysics, Golden, CO, United States, Eojin Lee, Columbia University, New York City, United States, Whyjay Zheng, Cornell University, Earth and Atmospheric Sciences, Ithaca, NY, United States, Michael Field, University of Florida, Ft Walton Beach, United States, Elena Savidge, University of Victoria, School of Earth and Ocean Sciences, Victoria, BC, Canada, Facundo Sapienza, University of California, Berkeley, Statistics, Berkeley, United States, Shane Grigsby, UC Santa Barbara, Santa Barbara, CA, United States, Jonathan Taylor, Stanford University, Statistics, Stanford, United States, Matthew Siegfried, Colorado School of Mines, Department of Geophysics, Hydrologic Science & Engineering Program, Golden, CO, United States and Fernando Perez, University of California, Berkeley, Statistics, Berkeley, CA, United States
 
Automatic Gravity Wave Detection on the Ross Ice Shelf Using Supervised Panoptic Spectrogram Segmentation (1170849)
Shivansh Baveja1,2, Dhiman Ranjan Mondal3, Pedro Elosegui1, Chester A Ruszczyk1 and John Barrett1, (1)MIT Haystack Observatory, Westford, United States, (2)University of California Berkeley, Berkeley, CA, United States, (3)MIT Haystack Observatory, Westford, MA, United States
 
AutoTerm: A glacier termini dataset delineated automatically from Big Data based on Deep Learning (1135996)
Enze Zhang, The University of Texas at Austin, Austin, United States, Ginny A Catania, University of Texas at Austin, Austin, TX, United States and Daniel T Trugman, University of Nevada Reno, Nevada Seismological Laboratory, Reno, United States
 
Bidirectional Long Short-Term Memory Network to Attribute Greenland Ice Albedo Variability to Specific Drivers (1157309)
Raf Antwerpen1, Marco Tedesco1, Pierre Gentine2 and Patrick M Alexander3, (1)Columbia University, Lamont-Doherty Earth Observatory, Palisades, NY, United States, (2)Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States, (3)Columbia University, Lamont-Doherty Earth Observatory, Palisades, United States
 
Bridging Gaps in the Climate Observation Network: A Physics-based Nonlinear Dynamical Interpolation of Lagrangian Ice Floe Measurements via Data-Driven Stochastic Models (1099320)
Jeffrey Covington1, Nan Chen1 and Monica M. Wilhelmus2, (1)University of Wisconsin-Madison, Department of Mathematics, Madison, United States, (2)Brown University, Providence, United States
 
Can We Estimate Global Ice Volume Using Only Data, i.e., Without Using Physical Models? (1193925)
Simon Hans Edasi, Lynnwood, WA, UNITED STATES and Bradley Paul Lipovsky, University of Washington, Department of Earth and Space Sciences, Seattle, United States
 
Bridging Antarctic observations and models with deep learning (Invited) (1045952)
Ching-Yao Lai1, Yongji Wang2 and Yunona Iwasaki1, (1)Princeton University, Princeton, NJ, United States, (2)Princeton University, Princeton, United States
 
Clustering Behavior of Physics-Informed Neural Networks: Inverse Modeling of An Idealized Ice Shelf (1078020)
Yunona Iwasaki, Princeton University, Princeton, NJ, United States and Ching-Yao Lai, Princeton University, Princeton, United States
 
Developing an Enhanced Global Record of Soil Specific Freeze/Thaw States (1045715)
Jeremy M Johnston, University of New Hampshire Main Campus, Durham, NH, United States, Paul Houser, George Mason University Fairfax, Geography and Geoinformation Sciences, Fairfax, VA, United States, Viviana Maggioni, George Mason University Fairfax, Sid and Reva Dewberry Department of Civil, Environmental, and Infrastructure Engineering, Fairfax, VA, United States and Jonas Lembrechts, University of Antwerp, Wilrijk, BE, Belgium
 
Discovery of ice shelf rheology via physics-informed neural network (1064571)
Yongji Wang and Ching-Yao Lai, Princeton University, Princeton, United States
 
Evaluating the Contribution of Ocean Variables in an Updated Markov Model for Antarctic Sea Ice Predictability (1172316)
Bernard Wang, New York, NY, UNITED STATES, Xiaojun Yuan, Lamont-Doherty Earth Observ, Palisades, NY, United States and Cuihua Li, Lamont Doherty Earth Observ, Palisades, NY, United States
 
Feasibility to Accelerate Random Media Scattering with Physics Driven Artificial Intelligence (1103752)
Xin Lv1, Chunzeng Luo2 and Shurun Tan1, (1)Zhejiang University, Zhejiang University/University of Illinois at Urbana-Champaign Institute, Haining, China, (2)Zhejiang University, Zhejiang University/University of Illinois at Urbana-Champaign Institute, Hangzhou, China
 
Forecasting Glacier Terminus Retreat Using Machine Learning (1073014)
Kevin Shionalyn, University of Texas at Austin, Austin, United States, Ginny A Catania, University of Texas at Austin, Austin, TX, United States; University of Texas, Institute for Geophysics, Austin, United States, Daniel T Trugman, Los Alamos National Laboratory, Los Alamos, United States and Michael Wood, JPL/NASA/Caltech, Pasadena, CA, United States
 
Functional Inversion of Glacier Rheology from Ice Velocities using ODINN.jl (1142894)
Facundo Sapienza, University of California, Berkeley, Statistics, Berkeley, United States, Jordi Bolibar, Utrecht University, Institute for Marine and Atmospheric Research, Utrecht, Netherlands, Fabien Maussion, University of Innsbruck, Innsbruck, Austria, Redouane Lguensat, Institut des Géosciences de l'Environnement, CNRS/Univ. Grenoble Alpes/G-INP/IRD, Grenoble, France, Fernando Perez, University of California, Berkeley, Statistics, Berkeley, CA, United States and Bert Wouters, IMAU/TU Delft, Utrecht/Delft, Netherlands
 
Future (2015-2100) Ice-Shelf Firn Air Depletion from a Statistical Firn Emulator (1135783)
Devon R Dunmire1, Nander Wever2, Alison F Banwell3, Jan Lenaerts2 and Megan Thompson-Munson2, (1)University of Colorado Boulder, Department of Atmospheric and Oceanic Sciences, Boulder, CO, United States, (2)University of Colorado Boulder, Department of Atmospheric and Oceanic Sciences, Boulder, United States, (3)University of Colorado Boulder, Cooperative Institute for Research in Environmental Sciences, Boulder, United States
 
Generating Antarctic Sub-shelf Melt Using Recurrent Neural Network-based Generative Adversarial Networks on Spatiotemporal Pixel Clusters (1197642)
Jacquelyn Shelton, Hong Kong Polytechnic University, Land Surveying and Geo-Informatics, Hong Kong, Hong Kong, Alexander Robel, Georgia Institute of Technology Main Campus, Earth and Atmospheric Science, Atlanta, United States, Matthew J Hoffman, Los Alamos National Laboratory, Fluid Dynamics and Solid Mechanics, Los Alamos, United States and Stephen F Price, Los Alamos National Laboratory, Los Alamos, NM, United States
 
Geometric features of mountain glaciers from 3D point clouds to delimit their extent: insight from gradient boosting trees algorithms (1101981)
Jesus Revuelto1, Jorge García Jiménez1, Francisco Rojas-Heredia1, Ixeia Vidaller1, César Deschamps-Berger1, Eñaut Izagirre2, Annelies Voordendag3 and Juan Ignacio López4, (1)Instituto Pirenaico de Ecología, Zaragoza, Spain, (2)Univerisidad del Pais Vasco, Vitoria, Spain, (3)Universität Innsbruck, Innsbruck, Austria, (4)Spanish Research Council, Zaragoza, Spain
 
How Transferable are Our Models? A Case Study of Idaho SNOTEL Sites (1179928)
Ibrahim Olalekan Alabi1, Hans-Peter Marshall2, Jodi Mead1 and Evi Ofekeze1, (1)Boise State University, Boise, ID, United States, (2)Boise State University, Department of Geosciences, Boise, ID, United States
 
IGM, a data assimilation and Glacier Evolution Model Accelerated by Deep-learning and GPU (Invited) (1094186)
Guillaume Jouvet, Lausanne, Vaud, SWITZERLAND, Guillaume Cordonnier, Université Côte d'Azur, Sophia-Antipolis, France, Byungsoo Kim, ETH Zurich, Computer Graphics Laboratory, Zurich, Switzerland, Martin P Luethi, ETH Zurich, Zurich, Switzerland; University of Zurich, Geographical Institute, Zurich, Switzerland, Andreas Vieli, University of Zurich, Zurich, Switzerland and Andy Aschwanden, University of Alaska Fairbanks, Fairbanks, AK, United States
 
Initial insights from two broadband arrays straddling the Thwaites Glacier eastern shear margin (1192934)
Jacob I Walter1, Lucia Fernanda Gonzalez2, Emma C Smith3, Marianne S. Karplus2, Adam D Booth4, Nori Nakata5 and Thwaites Interdisciplinary Margin Evolution (TIME) Team, (1)Oklahoma Geological Survey, University of Oklahoma, Norman, United States, (2)University of Texas at El Paso, Geological Sciences, El Paso, TX, United States, (3)University of Leeds, Leeds, LS2, United Kingdom, (4)University of Leeds, Leeds, United Kingdom, (5)Lawrence Berkeley National Laboratory, Berkeley, United States
 
Learning the glacier firn density structure (1200395)
Ayobami Ogunmolasuyi, Dartmouth College, Hanover, NH, United States and Colin Meyer, Dartmouth College, Thayer School of Engineering, Hanover, United States
 
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow (1069303)
Michael Field, Colorado School of Mines, Geophysics, Golden, United States; University of Florida, Ft Walton Beach, United States, Tasha Snow, Colorado School of Mines, Geophysics, Golden, CO, United States, Ellianna Abrahams, University of California Berkeley, Statistics, Berkeley, CA, United States, Eojin Lee, Columbia University, New York City, United States, Celia Baumhoer, German Aerospace Center (DLR), Land Surface Dynamics, Oberpfaffenhofen, Germany and Matthew Siegfried, Colorado School of Mines, Department of Geophysics, Hydrologic Science & Engineering Program, Golden, CO, United States
 
Mapping Retrogressive Thaw Sumps (RTS) Using Transformer-Based Neural Networks (1154973)
Ridhima Singh1, Yili Yang2 and Brendan M Rogers2, (1)Farragut High School, Knoxville, TN, United States, (2)Woodwell Climate Research Center, Falmouth, United States
 
MIML-Ice: A Multi-Instance Multi-Label Learning Method for Polygon-Level Sea Ice Classification (1153393)
Samira Alkaee Taleghan1, Behzad Vahedi2, Morteza Karimzadeh2, Andrew Barrett3, Walt Meier4, Siri Jodha S Khalsa3 and Farnoush Banaei-Kashani5, (1)College of Engineering, Design and Computing, University of Colorado Denver, Denver, United States, (2)University of Colorado Boulder, Department of Geography, Boulder, CO, United States, (3)National Snow and Ice Data Center (NSIDC), CIRES, University of Colorado Boulder, Boulder, United States, (4)National Snow and Ice Data Center, CIRES, University of Colorado Boulder, Boulder, CO, United States, (5)College of Engineering, Design and Computing,University of Colorado Denver, Denver, CO, United States
 
Observing Supraglacial Lakes Using Semantic Segmentation and PlanetScope Imagery (1070610)
Lillianne Thomas1, Slesa Adhikari2, Iksha Gurung3, Manil Maskey4, Rahul Ramachandran5, Aaron S Kaulfus5 and Muthukumaran Ramasubramanian3, (1)Development Seed, Venice, CA, United States, (2)The University of Alabama in Huntsville, Huntsville, United States, (3)University of Alabama in Huntsville, Huntsville, AL, United States, (4)NASA, Huntsville, United States, (5)NASA Marshall Space Flight Center, Huntsville, United States
 
Pleistocene Antarctic Iceberg History at IODP Sites U1536 and U1537 Quantified by Convolutional Neural Networks (1072996)
Claire E Jasper, Lamont -Doherty Earth Observatory, Palisades, United States; Columbia University, New York, United States, Maureen E Raymo, Columbia University, Lamont-Doherty Earth Observatory, Palisades, United States, Maya Tessler, Barnard College, New York, United States; Louisiana State University, Baton Rouge, United States and Blake Dyer, University of Victoria, Earth and Ocean Sciences, Victoria, BC, Canada
 
Probabilistic Machine Learning for Automated Ice Core Dating (1144434)
Aditya Ravuri1, Tom Andersson2, Markus Kaiser1, Ieva Kazlauskaite1, Max Fryer1, J Scott Hosking2, Mark Girolami1 and Neil D Lawrence1, (1)University of Cambridge, Cambridge, United Kingdom, (2)NERC British Antarctic Survey, Cambridge, United Kingdom
 
Quantifying Ice Damage in Antarctic Ice Shelves from Satellite Observations Using a Neural Network (1108026)
Martin Wearing1, Daniel Goldberg2, Noel Gourmelen2, Ching-Yao Lai3, Jowan Menhinick Barnes4, Martin Ewart5 and Alex Horton5, (1)University of Edinburgh, Edinburgh, United Kingdom, (2)University of Edinburgh, School of Geosciences, Edinburgh, United Kingdom, (3)Princeton University, Princeton, United States, (4)Northumbria University, Geography and Environmental Sciences, Newcastle-Upon-Tyne, United Kingdom, (5)Earthwave Ltd, Edinburgh, United Kingdom
 
Revisiting glacier mass-balance sensitivity to surface air temperature using a data-driven regionalization (1106300)
Alfonso Fernandez, University of Concepcion, Concepcion, Chile and Marcelo A Somos-Valenzuela, University of La Frontera, Butamallin Research Center for Global Change, Temuco, Chile
 
Semantic Segmentation of Sea Ice Using Multi-scale Spatial Context (1193367)
Behzad Vahedi1, Rafael Pires de Lima2, Benjamin Lucas1 and Morteza Karimzadeh1, (1)University of Colorado Boulder, Department of Geography, Boulder, CO, United States, (2)University of Colorado at Boulder, Geography, Boulder, United States
 
SNOBENCH: Standardized Datasets, Benchmarks, and Software for Data-Driven Snowpack Estimation (1171510)
Colorado Reed1, Marianne Cowherd2, Shiheng Duan3, Ritwik Gupta1, Daniel Feldman4, Manuela Girotto5, Trevor Darrell1, Kurt Keutzer1, Alberto Todeschini6, Joseph Spisak7, Ammar Rizvi7, Sean Metzger1, Puya Vahabi1, Araav Patel1, Matt Uyttendaele7 and Salvatore Candido7, (1)University of California Berkeley, Berkeley, United States, (2)University of California Berkeley, Environmental Science, Policy, and Management, Berkeley, United States, (3)Lawrence Livermore National Laboratory, Livermore, United States, (4)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (5)University of California Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States, (6)UC Berkeley, Berkeley, CA, United States, (7)Meta AI, Menlo Park, United States
 
Sub-seasonal prediction of Arctic sea ice concentration using time series forecasting technique (1140023)
Ha-Rim Kim, Ewha Womans University, Seoul, Korea, Republic of (South), Junghyun Park, Pukyong National University, Busan, South Korea and Baek-Min Kim, Pukyong National University, Pusan, South Korea
 
TexStructCNN - a Deep Learning based Image Segmentation Technique for Permafrost Landscape Characterization (1145127)
Anjishnu Mahanta, Subrat Kishore Dutta, Harini Nagendra and Santonu Goswami, Azim Premji University, Centre for Climate Change and Sustainability, Bangalore, India
 
UNDERSTANDING DRIVERS OF GREENLAND SURFACE MELTING THROUGH MACHINE LEARNING, GAME THEORY AND ATTRIBUTION ANALYSIS: A TEST CASE AT THE HELHEIM GLACIER (1105618)
Marco Tedesco, Lamont-Doherty Earth Observatory, Columbia University, New York, NY, United States, Patrick Alexander, Lamont -Doherty Earth Observatory, Columbia University, Palisades, NY, United States, Raf Antwerpen, Columbia University, Lamont-Doherty Earth Observatory, Palisades, NY, United States and Bingkun Luo, RSMAS, Meteorology and Physical Oceanography, Miami, United States
 
Unveiling lake ice phenology in Central Asia with MODIS data and a machine learning approach (1101942)
Yuancheng Xu, Xingdong Li and Di Long, Tsinghua University, Department of Hydraulic Engineering, Beijing, China
 
Using Deep Learning to Predict Systematic Model Error from Sea Ice Data Assimilation Increments in a Fully Coupled Climate Model (1178901)
William Gregory1, Mitchell Bushuk2, Yong-Fei Zhang1 and Alistair Adcroft3, (1)Princeton University, Princeton, NJ, United States, (2)NOAA/Geophysical Fluid Dynamics Laboratory, Princeton, NJ, United States, (3)Princeton University, Program in Atmospheric and Oceanic Sciences, Princeton, United States
 
Using Deep Machine Learning Hydrological Models to Investigate How Glaciers Modify the Streamflow Response to Heatwaves (1049765)
Sam Anderson, University of British Columbia, Earth, Ocean and Atmospheric Sciences, Vancouver, BC, Canada and Valentina Radic, University of British Columbia, Vancouver, BC, Canada
 
Using Self Organizing Maps to identify mechanisms for future increases in wintertime sea ice in the Ross Sea, Antarctica (1123357)
Alice K DuVivier1, Maria J Molina2,3, Laura Landrum1, Marika M Holland1 and Kristen M. Krumhardt3, (1)National Center for Atmospheric Research, Boulder, CO, United States, (2)University of Maryland, College Park, United States, (3)National Center for Atmospheric Research, Boulder, United States
 
Variational Inference of Ice Shelf Rheology with Physics-Informed Machine Learning (1133974)
Bryan V Riel, Zhejiang University, School of Earth Sciences, Hangzhou, China and Brent Minchew, Massachusetts Institute of Technology, Department of Earth, Atmospheric and Planetary Sciences, Cambridge, MA, United States
 
X-band COSMO-SkyMed Data Grounding Line Mapping Using Deep Learning (1075081)
Natalya Maslennikova, University of Houston, Houston, TX, United States, Pietro Milillo, University of Houston, Department of Civil and Environmental Engineering, Houston, United States, Luigi Dini, Italian Space Agency, Matera, Italy, Yara Mohajerani, EnvAI Solutions Inc., Toronto, Canada; University of Washington, Civil and Environmental Engineering, Seattle, United States, Eric J Rignot, University of California Irvine, Department of Earth System Science, Irvine, United States; Jet Propulsion Laboratory, Pasadena, United States, Bernd Scheuchl, University of California Irvine, Irvine, CA, United States and Seongsu Jeong, University of California Irvine, Earth System Science, Irvine, United States
See more of: Cryosphere
<< Previous Session Proposal | Next Session Proposal >>