Monitoring supraglacial lake dynamics in Antarctica with machine learning

Kurzfassung

Monitoring supraglacial lake dynamics is important for understanding their impact on ice shelf stability and possible changes in the context of climate change. Supraglacial meltwater accumulation can drive accelerated ice discharge through various processes: surface runoff leading to ice thinning, basal meltwater injection causing basal sliding, and hydrofracture triggering ice shelf collapse and subsequent glacier acceleration. Furthermore, the increased presence of supraglacial lakes around the Antarctic margin can enhance melting due to the low albedo of lakes, which increases solar radiation absorption. Continuous monitoring is therefore essential for improving our understanding of the seasonal variations in the extent of supraglacial lakes, their effects on ice shelf stability, and the surface mass balance of ice sheets. Recently, supraglacial lake extent mapping efforts were initiated based on optical satellite data but circum-Antarctic data products providing intra-annual information on supraglacial lake dynamics are still missing. Here, we present a novel classification method for automated supraglacial lake extent delineation with Antarctic-wide mapping capabilities created within the ESA Lakes4Antarctica project. To tackle the lack of intra-annual supraglacial lake extent mappings for the entire Antarctic continent, two complementary mapping methods based on machine learning were developed to exploit the full archive of Sentinel-1 SAR and optical Sentinel-2 data. By using this multi-sensor lake extent mapping approach, we were able to overcome limitations of single-sensor data including frequent cloud coverage or polar darkness in optical imagery as well as wind roughening or speckle noise in SAR data. This novel approach allows the generation of recurrence maps of lake extents and bi-weekly statistics on supraglacial lake dynamics between the melting seasons 2015/2016 and 2023/2024 for ice shelves experiencing surface melt. Furthermore, the integration of supraglacial lake extents into modelling activities will be discussed to provide new insight into meltwater transport and routing across Antarctic ice shelves as well as in enhancing estimates of surface mass balance in the long-term.