C004
AI and automation techniques for large scale remote sensing of the cryosphere
Session ID#: 78239
Session Description:
The exponential increase in observations at high latitudes means that cryospheric environments are now being analyzed in unprecedented detail. However, the scales and rates at which data are being generated render many traditional approaches to analysis impractical. Cryospheric sciences are therefore increasingly requiring the development of automated and artificial intelligence (AI) for efficient analysis of these environments. The advent of platforms such as Google Earth Engine and Amazon Web Services means that such analyses are now highly accessible to the community. Significant potential therefore exists in the use of these techniques to gain substantial new insights into the changing cryosphere.
This session will bring together researchers using artificial intelligence, computer vision, or automated approaches to address questions from across glacier, ice sheet, sea ice and permafrost environments. In doing so it will share new approaches being taken by the community to large scale cryospheric research problems.
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
0758 Remote sensing [CRYOSPHERE]
0794 Instruments and techniques [CRYOSPHERE]
Primary Convener: Leigh A Stearns, University of Kansas, Department of Geology, Lawrence, KS, United States
Conveners: Soroush Rezvanbehbahani, University of Kansas, Department of Geology, Lawrence, KS, United States and James Lea, University of Liverpool, School of Environmental Sciences, Liverpool, L69, United Kingdom
Primary Liaison: Soroush Rezvanbehbahani, University of Kansas, Department of Geology, Lawrence, KS, United States
Using "Deep Learning" and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern Satellite Imagery (495721)
Lawrence J Hessburg IV, University of Colorado Boulder, Boulder, CO, United States, Connor Myers, University of Colorado at Boulder, Aerospace Engineering Sciences, Boulder, CO, United States, Ute C Herzfeld, Univ Colorado Boulder, Electrical, Computer and Energy Engineering and CIRES, Boulder, CO, United States and Tasha Markley, University of Colorado Boulder, ECEE, Boulder, CO, United States
Deep learning applied to glacier surface mass balance reconstruction and simulation (502442)
Jordi Bolibar1,2, Antoine Rabatel1, Isabelle Gouttevin3, Clovis Galiez4, Thomas Condom1 and Eric Sauquet2, (1)Univ. Grenoble Alpes, CNRS, IRD, Grenoble INP, Institut des Géosciences de l’Environnement (UMR 5001), F-38000, Grenoble, France, (2)Irstea, UR RiverLy, Lyon-Villeurbanne, France, (3)Météo-France-CNRS, CNRM-GAME UMR3589, Centre d'Études de la Neige (CEN), Grenoble, France, (4)Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, Grenoble, France, Grenoble, France
Greenland marine glacier terminus mapping in satellite imagery using the automated 2D Wavelet Transform Modulus Maxima (WTMM) segmentation method (502847)
Jukes Liu, Boise State University, Boise, ID, United States, Ellyn M Enderlin, Climate Change Institute, Orono, ME, United States and Andre Khalil, University of Maine, Chemical and Biomedical Engineering, Orono, ME, United States
Automatically delineating calving fronts of Greenland glaciers from multi-sensor remote sensing imagery: a general method based on deep learning (528451)
Enze Zhang1, Lin Liu2, Lingcao Huang1 and Ka Shing NG2, (1)The Chinese University of Hong Kong, Earth System Science Programme, Hong Kong, China, (2)The Chinese University of Hong Kong, Earth System Science Programme, Hong Kong, Hong Kong
Automating iceberg detection in Greenland using deep learning on high to moderate-resolution optical imagery (528816)
Soroush Rezvanbehbahani1, Leigh A Stearns1, Ramtin Keramati2 and Siddharth Shankar1, (1)University of Kansas, Department of Geology, Lawrence, KS, United States, (2)Stanford University, Department of Computational and Mathematical Engineering, Palo Alto, United States
Spatial variability of lateral stream channel migration over a valley-wide scale: Taylor Valley, Antarctica (537712)
M. Camille Barlow, University of Houston, Department of Civil & Environmental Engineering, National Center for Airborne Laser Mapping, Houston, TX, United States, Craig Glennie, University of Houston, Department of Civil and Environmental Engineering, Houston, TX, United States, Jennifer W Telling, University of Houston, Houston, TX, United States and Andrew G Fountain, Portland State University, Geology, Portland, OR, United States
A multi-decadal time series of Arctic glacier elevations from automated DEM processing (551442)
Robert W McNabb1, Christopher Nuth1, Romain Hugonnet2, Luc Girod1 and Andreas Kääb1, (1)University of Oslo, Department of Geosciences, Oslo, Norway, (2)Laboratoire d’Etudes en Géophysique et Océanographie Spatiales, Toulouse, France
Using time series of Sentinel-1 SAR observations to evaluate passive microwave melt detection methods over Antarctic Peninsula Ice Shelves (560035)
Andrew Carl Johnson, University of Alaska Fairbanks, Fairbanks, AK, United States, Mark A Fahnestock, University of Alaska Fairbanks, Geophysical Institute, Fairbanks, AK, United States and Regine Hock, Univ of AK-Geophysical Inst, Fairbanks, AK, United States
Inferring velocity variations from optical flow tracking at the Wolverine Glacier，South Central Alaska (564695)
Franklyn Dunbar, Anchorage, AK, United States, Douglas Brinkerhoff, University of Montana, Missoula, MT, United States and Shad O'Neel, USGS, Anchorage, AK, United States
CALFIN: A Calving Front Mask Dataset for East/West Greenland, 1972-2019 (575921)
Daniel Lop-Chi Cheng1, Eric Y Larour2 and Wayne Hayes1, (1)University of California Irvine, Irvine, CA, United States, (2)Jet Propulsion Laboratory, Pasadena, CA, United States
Monthly Velocity Map of Antarctica from Multiple SAR and Optical Remote Sensing Data with Hybrid Cloud Processing Pipeline (600704)
Seongsu Jeong1, Jeremie Mouginot2, Eric J Rignot2, Bernd Scheuchl3, Romain Millan4 and Anna Derkacheva5, (1)University of California Irvine, Earth System Science, Irvine, CA, United States, (2)University of California Irvine, Department of Earth System Science, Irvine, CA, United States, (3)University of California Irvine, Irvine, CA, United States, (4)University of Grenoble Alpes, Grenoble, France, (5)LGGE Laboratoire de Glaciologie et Géophysique de l’Environnement, Saint Martin d'Hères, France
Snow variability in southernmost Patagonia by a combination of spectral fusion and mixture analysis with machine learning approach using the Google Engine platform (603341)
Francisco Aguirre, Chilean Antarctic Institute, Scientific Department, Punta Arenas, Chile; Universidad de Magallanes, Centro de Investigación Gaia Antártica (CIGA), Punta Arenas, Chile, Sauter Tobias, University of Erlangen-Nuremberg, Geography, Erlangen, Germany, Christoph Schneider, Humboldt University of Berlin, Berlin, Germany, Ricardo Jaña, Instituto Antártico Chileno, Punta Arenas, Chile and Gino Casassa Sr., University of Magallanes, Punta Arenas, Chile
High-resolution machine-learning-based quantification of spatial heterogeneity in ice wedge polygon geomorphology (Invited) (612648)
Charles Abolt1,2, Michael Young2, Adam L Atchley1 and Cathy Jean Wilson1, (1)Los Alamos National Laboratory, Los Alamos, NM, United States, (2)University of Texas at Austin, Bureau of Economic Geology, Austin, TX, United States
Automated Delineation of Proglacial Lakes At Large Scale Utilizing Google Earth Engine Maximum-Likelihood Land Cover Classification (626458)
Anthony M Hengst, Appalachian State University, Department of Geological and Environmental Sciences, Boone, NC, United States and William H Armstrong Jr, Appalachian State University, Geological and Environmental Sciences, Boone, NC, United States
A Novel Hierarchical Learning Method for Remote Sensing Data with Applications of Greenland Ice Sheet Changes from Laser Altimetry (626490)
Prashant Shekhar1, Beata M Csatho2, Toni Schenk3, Abani K Patra1 and Eric Y Larour4, (1)University at Buffalo, Buffalo, NY, United States, (2)University at Buffalo, Department of Geology, Buffalo, NY, United States, (3)University at Buffalo, Buffalo, United States, (4)Jet Propulsion Laboratory, Pasadena, CA, United States
Machine and Deep Learning Identification of Crevasses on the Periphery of the Greenland Ice Sheet from ICESat Waveform Altimetry Data (630367)
Shane Grigsby, Cooperative Institute for Research in Environmental Sciences, Geography, Boulder, CO, United States, William T Colgan, Geological Survey of Denmark and Greenland, Copenhagen, Denmark, Waleed Abdalati, University of Colorado, Department of Geography, Boulder, CO, United States and Harihar Rajaram, Univ Colorado, Boulder, CO, United States
