Where the white continent Is blue: deep learning locates bare ice in Antarctica
Tollenaar, V.; Zekollari, H.; Pattyn, F.; Russwurm, M.; Kellenberger, B.; Lhermitte, S.; Izeboud, M.; Tuia, D. (2024). Where the white continent Is blue: deep learning locates bare ice in Antarctica. Geophys. Res. Lett. 51(3): e2023GL106285. https://dx.doi.org/10.1029/2023GL106285
In: Geophysical Research Letters. American Geophysical Union: Washington. ISSN 0094-8276; e-ISSN 1944-8007, more
|   |
| Author keywords |
blue ice; Antarctica; deep learning; noisy labels |
| Authors | | Top |
- Tollenaar, V., more
- Zekollari, H., more
- Pattyn, F., more
- Russwurm, M.
|
- Kellenberger, B.
- Lhermitte, S., more
- Izeboud, M.
- Tuia, D.
|
|
| Abstract |
In some areas of Antarctica, blue-colored bare ice is exposed at the surface. These blue ice areas (BIAs) can trap meteorites or old ice and are vital for understanding the climatic history. By combining multi-sensor remote sensing data (MODIS, RADARSAT-2, and TanDEM-X) in a deep learning framework, we map blue ice across the continent at 200-m resolution. We use a novel methodology for image segmentation with “noisy” labels to learn an underlying “clean” pattern with a neural network. In total, BIAs cover ca. 140,000 km2 (∼1%) of Antarctica, of which nearly 50% located within 20 km of the grounding line. There, the low albedo of blue ice enhances melt-water production and its mapping is crucial for mass balance studies that determine the stability of the ice sheet. Moreover, the map provides input for fieldwork missions and can act as constraint for other geophysical mapping efforts.
|
|
