Three years of near‐coastal Antarctic iceberg distribution from a machine learning approach applied to SAR imagery


Contact
maurobarbat [ at ] furg.br

Abstract

Mass loss around the Antarctic Ice Sheet is driven by basal melting and iceberg calving,which constitute the two dominant paths of freshwater flux into the Southern Ocean. Although of similarmagnitude, icebergs play an important and still not fully understood role in the balance of heat andfreshwater around Antarctica. This lack of understanding is partly due to operational difficulties inlarge-scale monitoring in polar regions, despite observational and remote sensing efforts. In this study, anovel machine learning approach, augmented by visual inspection, was applied to three SyntheticAperture Radar (SAR) mosaics of the whole Antarctic continent and its adjacent coastal zone. Althoughoriginally intended for a mapping of the Antarctic continent, the SAR mosaics allow us to document theevolution and distribution of the size (and mass) of icebergs in the pan-Antarctic near-coastal zone for theyears 1997, 2000, and 2008. Our novel algorithm identified 7,649 icebergs in 1997, 13,712 icebergs in 2000,and 7,246 icebergs in 2008 with surface areas between 0.1 and 4,567.82 km2and total masses of 4,641.53,6,862.81, and 5,263.69 Gt, respectively. Large regional variability was observed, although a zonal patterndistribution is present. This has implications for future climate modeling studies that try to estimate thefreshwater flux from melting icebergs, which demands a realistic representation of the interannuallyvarying near-coastal iceberg pattern to initialize the simulations.



Item Type
Article
Authors
Divisions
Primary Division
Programs
Primary Topic
Publication Status
Published
Eprint ID
50401
DOI 10.1029/2019JC015205

Cite as
Barbat, M. M. , Rackow, T. , Hellmer, H. , Wesche, C. and Mata, M. M. (2019): Three years of near‐coastal Antarctic iceberg distribution from a machine learning approach applied to SAR imagery , Journal of Geophysical Research: Oceans . doi: 10.1029/2019JC015205


Share
Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Citation

Geographical region

Research Platforms
N/A

Campaigns
N/A


Actions
Edit Item Edit Item