Applications of AI/ML in Geodesy

Nerem, R Steven

G003
Applications of AI/ML in Geodesy

Session ID#: 251747

Session Description:

Artificial intelligence and machine learning have become important tools for understanding patterns and signals in large volumes of data, and so it is natural that these techniques are beginning to be applied to analyze geodetic data. This session seeks talks on a broad variety of applications of AI/ML in geodesy including earth surface, natural hazard and climate change monitoring. AI/ML is exceptionally suited for tackling challenges such as pattern classification, dynamic time series modeling, short-term forecasting, downscaling, and data fusion. The expanding volume of geodetic data, including highly-resolved GNSS time series, InSAR deformation maps, and satellite gravimetry and altimetry products, alongside enriched auxiliary data from advanced weather and environmental models, increasingly favors AI/ML methodologies. Contributions that highlight new advancements in efficient deep learning algorithms, efforts toward explainable AI, and the integration of physical information into data-driven frameworks are especially encouraged.

Co-Sponsor(s):

IN - Informatics

Index Terms:

1295 Integrations of techniques [GEODESY AND GRAVITY]
1299 General or miscellaneous [GEODESY AND GRAVITY]
1920 Emerging informatics technologies [INFORMATICS]
1942 Machine learning [INFORMATICS]

Primary Convener: R Steven Nerem, Smead Aerospace Engineering Sciences, Colorado Center for Astrodynamics Research, University of Colorado Boulder, Boulder, CO, United States

Conveners: Jade Morton, University of Colorado Boulder, Ann and H.J. Smead Aerospace Engineering Sciences, Boulder, United States and Benedikt Soja, ETH Zurich, Institute of Geodesy and Photogrammetry, Zurich, Switzerland

Bathymetry Prediction with SWOT Gravity Anomaly using Machine Learning Methods (Invited) (1891356)

David T Sandwell¹, Benjamin James Phrampus², Bjarke Nilsson³, Yao Yu⁴, Farshad Salajegheh⁵, Hugh Harper⁶, Biao Liu³, Ole Baltazar Andersen³, Walter H F Smith⁷, Paul Elmore⁸, James Beale⁹, Luis Altamirano¹⁰, Jonathan Kirby³ and Jamie Roberts⁶, (1)Scripps Institution of Oceanography, University of California San Diego, Institute of Geophysics and Planetary Physics, La Jolla, United States, (2)US Naval Research Laboratory, Ocean Sciences Division, Stennis, United States, (3)DTU Space, Lyngby, Denmark, (4)Scripps Institution of Oceanography, Institute of Geophysics and Planetary Physics, La Jolla, United States, (5)University of Newcastle, Callaghan, Australia, (6)National Geospatial Intelligence Agency, Springfield, United States, (7)NOAA Lab Satellite Altimetry, College Park, MD, United States, (8)Applied Physics Laboratory Johns Hopkins, Laurel, United States, (9)National Geospatial Intelligence Agency, St. Louis, United States, (10)The University of Southern Mississippi, School of Ocean Science and Engineering, Stennis Space Center, United States

Evaluation of Temporal Deep Learning Models for Ionospheric Delay Estimation and Their Impact on GNSS Positioning Accuracy (1909611)

Soo-Hyeon Lim and Tae-Suk Bae, Sejong University, Geoinformation Engineering, Seoul, South Korea

Probabilistic Neural Networks for Atmospheric Delay Modeling: Enhancing GNSS Positioning with Uncertainty-Aware Corrections (1916507)

Benedikt Soja¹, Tomasz Hadaś², Raul Orus Perez³, Muhammad Arqim Adil², Matthias Aichinger-Rosenberger¹, Laura Crocetti¹, Junyang Gou¹, Kamil Kaźmierski², Grzegorz Marut², Shuyin Mao¹, Arno Rüegg¹ and Matthias Schartner¹, (1)Institute of Geodesy and Photogrammetry, ETH Zurich, Zurich, Switzerland, (2)Institute of Geodesy and Geoinformatics, Wrocław University of Environmental and Life Sciences, Wrocław, Poland, (3)Wave Interaction and Propagation Section, ESA-ESTEC, Noordwijk, Netherlands

A machine learning framework to map Atmospheric Rivers using space- and ground-based GNSS observations (1937231)

Endrit Shehaj¹, Stephen Sylvain Leroy², Kerri Cahoy¹ and Benedikt Soja³, (1)Massachusetts Institute of Technology, Cambridge, MA, United States, (2)Atmospheric and Environmental Research, Inc., Lexington, MA, United States, (3)Institute of Geodesy and Photogrammetry, ETH Zurich, Zurich, Switzerland

Ultra-short-term UT1-UTC predictions: A machine learning approach using VLBI Intensives (1945744)

Arnab Laha¹, Matthias Schartner², Junyang Gou², Benedikt Soja² and Onkar Dikshit¹, (1)Indian Institute of Technology Kanpur, Department of Civil Engineering, Kanpur, India, (2)Institute of Geodesy and Photogrammetry, ETH Zurich, Zurich, Switzerland

Subsurface Triggers of Land Subsidence in the Rhineland Coalfield, Western Germany: Insights from Machine Learning and geotechnical modeling (1951873)

DK Ritushree¹, Marzieh Baes² and Mahdi Motagh², (1)GFZ Helmholtz Centre for Geosciences, Potsdam, Bradenburg, GERMANY, (2)GFZ Helmholtz Center for Geosciences, Potsdam, Germany

Enhancing GGM Coefficients for Precise Geoid Modeling Using PINN (1955302)

John Akutcha and Ahmed Abdalla, Louisiana State University, Department of Civil and Environmental Engineering, Baton Rouge, United States

High-Resolution Inland Surface Water Mapping Using GNSS Reflectometry and Deep Learning (Invited) (1961027)

Zhuoyi Zhao, University of Colorado Boulder, Smead Aerospace Engineering Sciences, Boulder, United States and Jade Morton, University of Colorado Boulder, Ann and H.J. Smead Aerospace Engineering Sciences, Boulder, United States

Uncertainty Quantification of Satellite-based Essential Climate Variables Derived from Deep Learning: Examples of Snow Cover and Terrestrial Water Storage (1970778)

Junyang Gou¹, Arnt-Børre Alberg², Mostafa Kiani Shahvandi¹, Mohammad J. Tourian³, Ulrich Meyer⁴, Eva Boergens⁵, Isabella Velicogna^6,7, Anders U. Waldeland², Adrian Jaeggi⁴, Konrad Schindler¹, Benedikt Soja¹ and Fredrik Dahl², (1)Institute of Geodesy and Photogrammetry, ETH Zurich, Zurich, Switzerland, (2)Norwegian Computing Center, Oslo, Norway, (3)Institute of Geodesy, University of Stuttgart, Stuttgart, Germany, (4)Astronomical Institute, University of Bern, Bern, Switzerland, (5)GFZ Helmholtz Centre for Geosciences, Potsdam, Germany, (6)Department of Earth System Science, University of California Irvine, Irvine, United States, (7)NASA Jet Propulsion Laboratory, Pasadena, CA, United States

Detecting Millimeter-Scale Offsets in GNSS Time Series: Benchmarking a Two-Stage Statistical Test against XGBoost and Quantifying Velocity Bias (1981362)

Yaser Rahmani, University of Utah, Geology and Geophysics, Salt Lake City, United States and Tonie M van Dam, University of Utah, Department of Geology and Geophysics, Salt Lake City, United States

Machine Learning Based Offset Detection in Vertical GPS Time Series (1981392)

Zachary Young, University of Montana, Department of Geosciences, Missoula, MT, United States, Zachary Harwood Hoylman, University of Montana, Franke School of Forestry and Conservation, Missoula, United States, Hilary R Martens, Department of Geosciences, University of Montana, Missoula, United States and William P Gardner, University of Montana, Missoula, MT, United States

Extreme Weather Tracking and Prediction of Flash Floods using GNSS Troposphere Observations and Machine Learning Models in Near Real Time (1991058)

Yehuda Bock¹, Bhavik Chandna¹, Rohith Reddy Rachala¹, Umaa Rebbapragada², Angelyn W Moore³, Joe T Roberts³, Fred J Calef III³, Zhen Liu³, Ivory J Small⁴, Jayme L Laber⁵ and Robert Munroe⁶, (1)Scripps Institution of Oceanography, University of California San Diego, Institute of Geophysics and Planetary Physics, La Jolla, United States, (2)Jet Propulsion Laboratory, California Institute of Technology, Machine Learning and Instrument Autonomy, Pasadena, United States, (3)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (4)NOAA, National Weather Service, San Diego, United States, (5)NOAA National Weather Service, Oxnard, CA, United States, (6)NOAA, National Weather Service, Los Angeles Weather Forecast Office, Los Angeles, United States

A Machine Learning-Based Exploration of Modelling VLBI Station Displacements (1997278)

Shivangi Singh¹, Johannes Boehm², Hana Krasna², Sigrid Boehm², Nagarajan B¹ and Onkar Dikshit¹, (1)Indian Institute of Technology Kanpur, Department of Civil Engineering, Kanpur, India, (2)Technische Universität Wien, Department of Geodesy and Geoinformation, Vienna, Austria

See more of: Geodesy

<< Previous Session Proposal | Next Session Proposal >>

G003 Applications of AI/ML in Geodesy

Session Description:

Co-Sponsor(s):

Index Terms:

G003
Applications of AI/ML in Geodesy