Pan-Arctic Sea Ice Concentration from SAR and Passive Microwave
Arctic sea ice monitoring is a fundamental prerequisite for anticipating and mitigating the impacts of climate change. Satellite-based sea ice observations have been subject to intense attention over the last few decades, with passive microwave (PMW) radiometers being the primary sensors for retriev...
Main Authors: | , , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5194/egusphere-2024-178 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-178/ |
Summary: | Arctic sea ice monitoring is a fundamental prerequisite for anticipating and mitigating the impacts of climate change. Satellite-based sea ice observations have been subject to intense attention over the last few decades, with passive microwave (PMW) radiometers being the primary sensors for retrieving pan-Arctic sea ice concentration, albeit with coarse spatial resolutions of a few or even tens of kilometers. Space-borne Synthetic Aperture Radar (SAR) missions, such as Sentinel-1, provide dual-polarized C-band images with <100 meter spatial resolution, which are particularly well-suited for retrieving high-resolution sea ice information. In recent years, deep learning-based vision methodologies have emerged with promising results for SAR-based sea ice concentration retrievals. Despite recent advancements, most contributions focus on regional or local applications without empirical studies on the generalization of the algorithms to the pan-Arctic region. Furthermore, many contributions omit uncertainty quantification from the retrieval methodologies, which is a prerequisite for the integration of automated SAR-based sea ice products into the workflows of the national ice services, or for the assimilation into numerical ocean-sea-ice coupled forecast models. Here, we present ASIP (Automated Sea Ice Products): a new and comprehensive deep learning-based methodology to retrieve high-resolution sea ice concentration with accompanying well-calibrated uncertainties from Sentinel-1 SAR and Advanced Microwave Scanning Radiometer 2 (AMSR2) passive microwave observations at a pan-Arctic scale for all seasons. We compiled a vast matched dataset of Sentinel-1 HH/HV imagery and AMSR2 brightness temperatures to train ASIP with regional ice charts as labels. ASIP achieves an R 2 -score of 95 % against a held-out test dataset of regional ice charts. In a comparative study against pan-Arctic ice charts and PMW-based sea ice products, we show that ASIP generalizes well to the pan-Arctic region. Additionally, the comparison ... |
---|