Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning

Abstract

Sea level rise contribution from the Antarctic ice sheet is influenced by changes in glacier and ice shelf front position. Still, little is known about seasonal glacier and ice shelf front fluctuations as the manual delineation of calving fronts from remote sensing imagery is very time-consuming. The major challenge of automatic calving front extraction is the low contrast between floating glacier and ice shelf fronts and the surrounding sea ice. Additionally, in previous decades, remote sensing imagery over the often cloud-covered Antarctic coastline was limited. Nowadays, an abundance of Sentinel-1 imagery over the Antarctic coastline exists and could be used for tracking glacier and ice shelf front movement. To exploit the available Sentinel-1 data, we developed a processing chain allowing automatic extraction of the Antarctic coastline from Seninel-1 imagery and the creation of dense time series to assess calving front change. The core of the proposed workflow is a modified version of the deep learning architecture U-Net. This convolutional neural network (CNN) performs a semantic segmentation on dual-pol Sentinel-1 data and the Antarctic TanDEM-X digital elevation model (DEM). The proposed method is tested for four training and test areas along the Antarctic coastline. The automatically extracted fronts deviate on average 78 m in training and 108 m test areas. Spatial and temporal transferability is demonstrated on an automatically extracted 15-month time series along the Getz Ice Shelf. Between May 2017 and July 2018, the fronts along the Getz Ice Shelf show mostly an advancing tendency with the fastest moving front of DeVicq Glacier with 726 ± 20 m/yr.

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

“…Even though this did not affect the classification results over the test regions, more timely coastline data would be desirable to prevent the described effects. In this context, automatically derived calving fronts from Sentinel-1 data over Antarctica (e.g., [85]) could be a valuable data source.…”

Time‐Varying Ice Sheet Mask: Implications on Ice‐Sheet Mass Balance and Crustal Uplift

“…This need should be weighed against data availability, in both time and space, the speed of methods to trace ice extent and time available to implement them, and the desired tolerance in ice‐mask‐induced uncertainty for a given mass‐balance estimate. Automatic methods to delineate calving fronts are an area of active research (e.g., Baumhoer et al., 2019; Cheng et al., 2020), and their application to both land‐terminating regions and smaller outlet glaciers could accelerate this process and decrease trade‐offs. Regardless, ice masks clearly need to be updated both more regularly and systematically than they presently are, so as to accurately gauge the mass‐balance of the Greenland Ice Sheet over longer periods.…”

A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning

“…For removal of false lake classifications seaward of the Antarctic coastline, a Sentinel-1 coastline product [34,49] was additionally integrated into post-classification. The circum-Antarctic coastline was derived from Sentinel-1 data covering the period June to August 2018 using an automated processing pipeline specifically developed for semantic segmentation of the Antarctic calving front based on a modified U-Net [34]. In detail, the coastline product represents the average coastline position over the given period.…”

“…CNNs are particularly suitable To overcome most of the described issues, we propose the use of a convolutional neural network (CNN) allowing to consider the spatial image context through convolutional extraction of feature maps from a given input image. CNNs are particularly suitable where traditional classification methods fail and were commonly used in computer vision and particularly for semantic segmentation and object detection tasks in remote sensing [31,32], e.g., for automated calving front detection using SAR and optical satellite imagery [33][34][35], for sea-land classification in optical satellite imagery [36], for multi-temporal crop type classification in optical Landsat imagery [37], for sea ice concentration estimation in dualpolarized RADARSAT-2 imagery [38], for automated mapping of ice-wedge polygons in high-resolution satellite and unmanned aerial vehicle images [39,40], or for building and road extraction in optical and aerial satellite imagery [41,42], to only name a few. In this study, we extract supraglacial lake extents from single-polarized Sentinel-1 imagery using a modified version of a CNN originally developed for semantic segmentation of biomedical images (U-Net) [43].…”