The crevasse dataset provides information on crevasse locations at 0.2 m spatial resolution for selected regions in the Alps. Information on crevasse locations is important for mountaineers and field researchers to plan a safe traverse over a glacier. This dataset is generated based on a multitask deep neural network for automated crevasse mapping from high-resolution airborne remote sensing imagery. The model was trained and evaluated over seven training and six test areas located in the Oetztal and Stubai Alps. By simultaneously preforming edge detection and segmentation tasks, the multitask model is able to robustly detect glacier crevasses of different shapes within different illumination conditions with a balanced accuracy of 86%. To prove large-scale applicability, this dataset includes high-resolution crevasse maps for the entire Oetztal and Stubai Alps based on imagery acquired within the years 2019 and 2020. Furthermore, high-quality crevasse maps for all glaciers surrounding Grossglockner, Piz Palue, and Ortler were generated for available imagery in the years 2022 and 2023, repsectively.
The here presented datasets can be integrated into hiking maps and digital cartography tools to provide mountaineers and field researcher with up-to-date crevasse information but also inform modelers on the distribution of stress within a glacier. Accompanying Publication: Baumhoer, C., Leibrock, S., Zapf, C., Beer, W., Kuenzer, C., in review. Automated crevasse mapping for Alpine glaciers: A multitask deep neural network approach. International Journal of Applied Earth Observation and Geoinformation.
Contacts:
Properties:
Items:
The layer depicts the glacier crevasse boundary at Grossglockner with a resolution of 0.2 meter.
The layer depicts the glacier crevasse boundary at Oetztal and Stubai with a resolution of 0.2 meter.
The layer depicts the glacier crevasse boundary at Ortler with a resolution of 0.2 meter.
The layer depicts the glacier crevasse boundary at Grossglockner with a resolution of 0.2 meter.