Articles | Volume 17, issue 11
https://doi.org/10.5194/tc-17-4675-2023
https://doi.org/10.5194/tc-17-4675-2023
Research article
 | 
09 Nov 2023
Research article |  | 09 Nov 2023

Mapping the extent of giant Antarctic icebergs with deep learning

Anne Braakmann-Folgmann, Andrew Shepherd, David Hogg, and Ella Redmond

Viewed

Total article views: 2,704 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,101 526 77 2,704 54 50
  • HTML: 2,101
  • PDF: 526
  • XML: 77
  • Total: 2,704
  • BibTeX: 54
  • EndNote: 50
Views and downloads (calculated since 11 May 2023)
Cumulative views and downloads (calculated since 11 May 2023)

Viewed (geographical distribution)

Total article views: 2,704 (including HTML, PDF, and XML) Thereof 2,662 with geography defined and 42 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 13 Jul 2024
Download
Short summary
In this study, we propose a deep neural network to map the extent of giant Antarctic icebergs in Sentinel-1 images automatically. While each manual delineation requires several minutes, our U-net takes less than 0.01 s. In terms of accuracy, we find that U-net outperforms two standard segmentation techniques (Otsu, k-means) in most metrics and is more robust to challenging scenes with sea ice, coast and other icebergs. The absolute median deviation in iceberg area across 191 images is 4.1 %.