New publication: Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle

An article by Johannes Lohse, Anthony P. Doulgeris and Wolfgang Dierking has been accepted for publication in Annals of Glaciology. The title of the publication is “Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle”.

In this study, we demonstrate a novel approach on how to incorporate per-class incidence angle effects in SAR backscatter intensity directly into the classification of sea-ice types. We train the classifier based on overlapping SAR and optical data to separate different ice types for Arctic-wide winter conditions. The results show improved classification accuracy compared to traditional methods.

Ongoing work is currently directed towards further development and improvement of the algorithm, aiming for robust and reliable computer-assisted ice charting in operational ice services.

The full article is available at https://doi.org/10.1017/aog.2020.45

Examples of mosaic classification results for the entire Arctic (top panel, based on 72 S1 images acquired on 3 and 4 March 2019) and a smaller region north of Svalbard (bottom panel, based on 3 S1 images acquired on 5 April 2018). S1 data are shown on the left (R = HV, G = HH and B = HH) and classification results on the right. The classified regions seamlessly overlap at image boundaries, indicating a successful per-class correction of IA effect.