AI4SeaIce: selecting loss functions for automated SAR sea ice concentration charting

Autor: Andrzej Kucik, Andreas Stokholm

Publikováno v: Scientific Reports, Vol 13, Iss 1, Pp 1-10 (2023)

Abstract For maritime navigation in the Arctic, sea ice charts are an essential tool, which still to this day is drawn manually by professional ice analysts. The total Sea Ice Concentration (SIC) is the primary descriptor of the charts and indicates

Externí odkaz: https://doaj.org/article/4eb9a3f6b76442fc8804037efbe07f02

AI4SeaIce:Towards Solving Ambiguous SAR Textures in Convolutional Neural Networks for Automatic Sea Ice Concentration Charting

Autor: Andreas Stokholm, Tore Wulf, Andrzej Kucik, Roberto Saldo, Jorgen Buus-Hinkler, Sine Munk Hvidegaard

Publikováno v: Stokholm, A, Wulf, T, Kucik, A, Saldo, R, Buus-Hinkler, J & Hvidegaard, S M 2022, ' AI4SeaIce : Towards Solving Ambiguous SAR Textures in Convolutional Neural Networks for Automatic Sea Ice Concentration Charting ', IEEE Transactions on Geoscience and Remote Sensing, vol. 60, 4304013 . https://doi.org/10.1109/TGRS.2022.3149323

Automatically producing arctic sea ice charts from Sentinel-1 Synthetic Aperture Radar (SAR) images is challenging for Convolutional Neural Networks (CNN) due to ambiguous backscattering signatures. The number of pixels viewed by the CNN model in the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e37ee4f2f04b1bbeb6646abfcc3a9f5d
https://orbit.dtu.dk/en/publications/12b46ae0-5054-4e56-8f9d-4f6ee849318b