🤖 AI Summary
To address low efficiency and poor consistency in glacier boundary extraction across large-scale, multi-temporal, and heterogeneous glacial environments, this study proposes GeoSAM-Glacier, the first semi-automated workflow for glacier mapping. The method integrates multi-temporal Sentinel-2 surface reflectance composites, spectral pre-screening using NDWI/NDSI, RGB-rendered prompting for segmentation, and post-processing constrained by terrain slope and radiometric physics. Its key innovation lies in the first adaptation of GeoSAM to glacier remote sensing interpretation, enabling synergistic integration of domain-specific remote sensing priors with foundation model segmentation capabilities. Applied to western Svalbard, the framework achieves high spatiotemporal consistency in annual glacier outline delineation, with excellent accuracy for major ice bodies; residual errors in small targets primarily stem from water bodies and cast shadows. Manual correction effort is reduced by over 70%. The framework demonstrates strong transferability across regions and sensor platforms.
📝 Abstract
Consistent glacier boundary delineation is essential for monitoring glacier change, yet many existing approaches are difficult to scale across long time series and heterogeneous environments. In this report, we present a GeoSAM-based, semi-automatic workflow for rapid glacier delineation from Sentinel-2 surface reflectance imagery. The method combines late-summer image compositing, spectral-index-based identification of candidate ice areas, prompt-guided segmentation using GeoSAM, and physically based post-processing to derive annual glacier outlines. The workflow is demonstrated in the Ny-Alesund and Kongsfjorden region of western Svalbard across multiple years of the Sentinel-2 era. Results show that the approach produces spatially coherent and temporally consistent outlines for major glacier bodies, while most errors are associated with small features affected by water bodies, terrain shadows, or high surface variability. The reliance on derived RGB imagery makes the method flexible and transferable to other optical datasets, with improved performance expected at higher spatial resolution. Although user inspection remains necessary to filter incorrect polygons and adjust thresholds for local conditions, the workflow provides a fast and practical alternative for multi-temporal glacier mapping and ice-loss assessment.