IceLines – A new data set of Antarctic ice shelf front positions

Abstract

The frontal position of an ice shelf is an important parameter for ice dynamic modelling, the computation of mass fluxes, mapping glacier area change, calculating iceberg production rates and the estimation of ice discharge to the ocean. Until now, continuous and up-to-date information on Antarctic calving front locations is scarce due to the time-consuming manual delineation of fronts and the previously limited amount of suitable earth observation data. Here, we present IceLines, a novel data set on Antarctic ice shelf front positions to assess calving front change at an unprecedented temporal and spatial resolution. More than 19,400 calving front positions were automatically extracted creating dense inter- and intra-annual time series of calving front change for the era of Sentinel-1 (2014-today). The calving front time series can be accessed via the EOC GeoService hosted by DLR and is updated on a monthly basis. For the first time, the presented IceLines data set provides the possibility to easily include calving front dynamics in scientific studies and modelling to improve our understanding about ice sheet dynamics.

A high-resolution calving front data product for marine-terminating glaciers in Svalbard

“…The calving front data product is mapped using the novel COBRA deep-learning model (Heidler et al, 2023). This model has been proven to outperform the previous calving front mapping models such as HED-UNet (Heidler et al, 2022), which was used for the IceLine Antarctic ice shelf front dataset (Baumhoer et al, 2023), CALFIN (Cheng et al, 2021), as well as the UNet model (Mohajerani et al, 2019). While the geomorphological features of tidewater glaciers in Svalbard and Greenland exhibit general similarities, it is important to note that the calving styles and neighbouring fjords can vary significantly among certain glaciers.…”

“…There is, therefore, a need for efficient automated methods. In recent years, deep learning has demonstrated promising capabilities in accurately mapping glacier calving fronts (Mohajerani et al, 2019a;Cheng et al, 2021;Heidler et al, 2022;Loebel et al, 2023;Gourmelon et al, 2022;Zhang et al, 2019;Baumhoer et al, 2019Baumhoer et al, , 2023. Mohajerani et al (2019) pioneered the application of deep learning in glacier calving front mapping by developing a U-Net architecture to isolate the calving front from satellite images.…”

A High-Resolution Calving Front Data Product for Marine-Terminating Glaciers in Svalbard

“…The calving front data product is mapped using the novel COBRA deep-learning model (Heidler et al, 2023). This model has been proven to outperform the previous calving front mapping models such as HED-UNet (Heidler et al, 2022), which was used for the IceLine Antarctic ice shelf front dataset (Baumhoer et al, 2023), CALFIN (Cheng et al, 2021), as well as the UNet model (Mohajerani et al, 2019). While the geomorphological features of tidewater glaciers in Svalbard and Greenland exhibit general similarities, it is important to note that the calving styles and neighbouring fjords can vary significantly among certain glaciers.…”

Mapping the extent of giant Antarctic icebergs with deep learning

“…Thus, just after calving, the iceberg would be within the former land mask and would not be picked up. A potential solution could be to always use the latest frontal positions from Baumhoer et al (2023) as a dynamic land mask. The last category of dark icebergs is the hardest and makes up 5 % of the overall dataset.…”