Year: 2026
Type: article
Abstract: Cryospheric mass movements (CMMs) are accelerating under rapid Arctic and high-mountain warming, yet understanding and predicting them remains challenging due to sparse observations, complex multi-scale processes, and shifting environmental baselines. This Perspective argues that machine learning should advance CMM science not only through prediction, but through transferable and physics-aware inference. We outline a roadmap centered on benchmark datasets, cross-scale generalization, and transdisciplinary collaboration for scientifically grounded hazard assessment.
Source: npj natural hazards.
Institutions: Stony Brook University, University of Alaska Fairbanks, University of Utah, Pennsylvania State University, City College of New York, University of Colorado Boulder, University of Houston, Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung, University of Sussex, GFZ Helmholtz Centre for Geosciences, UiT The Arctic University of Norway, University of Connecticut, International Arctic Research Center, Alaska Division of Geological and Geophysical Surveys, Wilfrid Laurier University, BGC Engineering (Canada)
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: gold
Estimated APC paid: $2,090
Awards: NNA Track 2: Collaborative Research: Planning for Infrastructure Resiliency and Adaptation amid Increasing Mass-Movement Risks across the Cryosphere, NNA Track 2: Collaborative Research: Planning for Infrastructure Resiliency and Adaptation amid Increasing Mass-Movement Risks across the Cryosphere
OpenAlex ID: W7155991608