SAR deep learning sea ice retrieval trained with airborne laser scanner measurements from the MOSAiC expedition

Abstract 0.5  m correlation length) and reflectance. It is shown that there is only a weak correlation between the radar backscatter and the sea ice topography. Accuracies between 44 % and 66 % and robustness between 71 % and 83 % give a realistic insight into the performance of modern convolutional neural network architectures across a range of ice conditions over 8 months. It also marks the first time algorithms have been trained entirely with labels from coincident measurements, allowing for a probabilistic class retrieval. The results show that segmentation models able to learn from the class distribution perform significantly better than pixel-wise classification approaches by nearly 20 % accuracy on average.

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: SAR deep learning sea ice retrieval trained with airborne laser scanner measurements from the MOSAiC expedition ; volume:18 ; number:5 ; year:2024 ; pages:2207-2222 ; extent:16 ; The Cryosphere ; 18, Heft 5 (2024), 2207-2222 (gesamt 16)

Contributors, Places and Time

• Creator: Kortum, Karl ; Singha, Suman ; Spreen, Gunnar ; Hutter, Nils ; Jutila, Arttu ; Haas, Christian

Further information

• DOI: 10.5194/tc-18-2207-2024
• URN: urn:nbn:de:101:1-2405090431412.029398882642
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 14.08.2025, 10:55 AM CEST