NH035
Toward Reliable and Scalable Geohazard Intelligence: From Multi-Scale Sensing to Open Data Foundations
Session ID#: 252469
Session Description:
To address the growing challenges of geohazards, we invite contributions that advance reliable and scalable machine learning/artificial intelligence (ML/AI) approaches for the detection, monitoring, and prediction of geohazards, such as earthquakes, tsunamis, volcanoes, landslides, and surface subsidence. We especially welcome works that (1) integrate multi-scale sensing technologies (e.g., remote sensing and distributed fiber-optic sensing) with ML/AI to support both pre- and post-event assessment of geohazards as well as their cascading impacts in diverse environmental settings, such as urbanized, remote, post-disturbance, and cold landscapes; (2) develop interpretable and knowledge-guided (e.g., physics-informed) ML/AI to reveal the driving factors and physical mechanisms; (3) evaluate and improve model robustness in extreme and data-scarce scenarios through cross-region and cross-scenario model transfer, uncertainty quantification, and real-time data fusion; and (4) develop open-source, multi-scale geohazard datasets to support the training and testing of foundation models toward reliable, scalable, real-world AI deployment.
Co-Sponsor(s):
Index Terms:
4307 Methods [NATURAL HAZARDS]
4315 Monitoring, forecasting, prediction [NATURAL HAZARDS]
4333 Disaster risk analysis and assessment [NATURAL HAZARDS]
4337 Remote sensing and disasters [NATURAL HAZARDS]
Primary Convener: Xin Wei, University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, MI, United States
Conveners: Chuxuan Li, University of California Los Angeles, Earth, Planetary, and Space Sciences, Los Angeles, CA, United States, Jingxiao Liu, Massachusetts Institute of Technology, Senseable City Laboratory, Cambridge, United States and Bingxu Luo, The University of Arizona, Geoscience, Tuscon, United States
Student/Early Career Convener: Ann Sinclair, Northwestern University, Earth, Environmental, & Planetary Sciences, Evanston, United States
Leveraging conventional and DAS seismic networks through novel processing paradigms (Invited) (1849625)
Ettore Biondi, Stanford University, Geophysics, Stanford, CA, United States, Jiaxuan Li, University of Houston, Houston, United States, Weiqiang Zhu, University of California, Berkeley, Department of Earth and Planetary Science, Berkeley, United States and Zhongwen Zhan, California Institute of Technology, Seismological Laboratory, Pasadena, United States
Foundational geospatial databases and long-term monitoring to support the next generation of data-driven landslide hazard and risk assessments (Invited Paper 1855640) (Invited) (1855640)
Benjamin B Mirus, U.S. Geological Survey, Geologic Hazards Science Center, Golden, United States, Jacob Woodard, University of Wisconsin-Madison, Geoscience, Madison, WI, United States, Max Sutton, Stanford University, Stanford, CA, United States, Lisa V Luna, Middlebury College, Albuquerque, United States, Xin Wei, University of Michigan, Michigan Institute for Data & AI in Society, Ann Arbor, United States, Prof. Sabine Loos, PhD, University of Michigan, Civil and Environmental Engineering Department, Michigan, United States and George E Hilley, Los Alamos National Lab, Los Alamos, United States
Exploring automatic segmentation of landslides using deep learning (1856760)
Hudson J Koch, Kentucky Geological Survey Lexington, Lexington, KY, United States, Junfeng Zhu, University of Kentucky, Kentucky Geological Survey, Lexington, United States and Jason Dortch, University of Kentucky, Kentucky Geological Survey, Lexington, KY, United States
Time-Series Landslide Detection with Multi-Scale Satellite Data and Unsupervised Machine Learning (1889428)
Yifan Sun, University of California Los Angeles, Department of Earth, Planetary, and Space Sciences, Los Angeles, United States, Seulgi Moon, University of California Los Angeles, Department of Earth, Planetary, and Space Sciences, Los Angeles, CA, United States, Louis Bouchard, University of California Los Angeles, Los Angeles, United States, Chuxuan Li, University of California Los Angeles, Earth, Planetary, and Space Sciences, Los Angeles, CA, United States, Alexander L Handwerger, UCLA, JIFRESSE; Jet Propulsion Lab, Los Angeles, United States and Gilles Peltzer, University of California Los Angeles, Earth Planetary and Space Sciences, Los Angeles, United States
Building a Community-Curated, Open-Access Platform of Global Landslide Datasets to Support Reliable and Scalable AI Models (1915796)
Xin Wei1, Reiko Chen2, Margaret Gereghty3, Elizabeth Bondi-Kelly2 and Prof. Sabine Loos, PhD3, (1)University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, MI, United States, (2)University of Michigan Ann Arbor, Electrical Engineering and Computer Science, Ann Arbor, United States, (3)University of Michigan Ann Arbor, Civil and Environmental Engineering, Ann Arbor, United States
A Hybrid Domain Adaptation Framework for Cross-Region Landslide Segmentation (1932958)
Rahul Deb, Stuyvesant High School, Queens Village, NY, UNITED STATES, Te Pei, Department of Civil Engineering, Stony Brook University, Department of Civil Engineering, New York, United States and Yingli Tian, Department of Electrical Engineering, The City College of the City University of New York, and CUNY-CREST, Department of Electrical Engineering, New York, United States
Integrating Machine Learning and Spatial Analytics for Landslide Detection and Monitoring with Satellite Images and Topographic Data (1936478)
Fuan Tsai, National Central University, Center for Space and Remote Sensing Research, Kanagawa, Japan, Shang-Nien Tsai, National Central University, Department of Civil Engineering, Zhongli, Taoyuan, Taiwan and Chi-Chuan Lo, National Central University, Center for Space and Remote Sensing Research, Zhongli, Taoyuan, Taiwan
AI-based fusion of multi-source data for earthquake damage assessment (1953356)
Xiao Yu1, Xie Hu2, Yuqi Song2 and Feng Lin2, (1)University of Illinois at Urbana-Champaign, Prairie Research Institute, Champaign, United States, (2)Peking University, College of Urban and Environmental Sciences, Beijing, China
A Machine Learning Benchmark Dataset for Generalizable Landslide Susceptibility Mapping (1980603)
Ryan Goldberg, CUNY City College of New York, Department of Electrical Engineering, New York, United States, Te Pei, Department of Civil Engineering, Stony Brook University, Department of Civil Engineering, New York, United States, Fred Moshary, CUNY City College, New York, United States and Yingli Tian, Department of Electrical Engineering, The City College of the City University of New York, and CUNY-CREST, Department of Electrical Engineering, New York, United States
Utilizing Multi-Model Training for Landslide Detection with Satellite Imagery (1982949)
Eric Song, Yale University, New Haven, CT, United States, Te Pei, Department of Civil Engineering, Stony Brook University, Department of Civil Engineering, New York, United States and Yingli Tian, Department of Electrical Engineering, The City College of the City University of New York, and CUNY-CREST, Department of Electrical Engineering, New York, United States
Multi-Scale Imagery and AI for Extreme Events: Integrating UAS and Ground-Level Sensing with Machine Learning for Post-Event Assessment (Invited) (1983069)
Joseph Wartman, University of Washington, Seattle, WA, United States, Barbaros Cetiner, University of California, Berkeley, Department of Civil and Environmental Engineering, Berkeley, United States and RAPID Facility
Improving Landslide Susceptibility Prediction with Terrain Patterns, High-Resolution Data, and Ensemble Models (1986652)
Jiangtao Liu1, Chaopeng Shen1, Te Pei2, Daniel Kifer3 and Kathryn Lawson1, (1)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, (2)Stony Brook University, Department of Civil Engineering, Stony Brook, United States, (3)Pennsylvania State University, Department of Computer Science & Engineering, University Park, United States
