Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

Abstract

Supraglacial lakes can have considerable impact on ice sheet mass balance and global sea-level-rise through ice shelf fracturing and subsequent glacier speedup. In Antarctica, the distribution and temporal development of supraglacial lakes as well as their potential contribution to increased ice mass loss remains largely unknown, requiring a detailed mapping of the Antarctic surface hydrological network. In this study, we employ a Machine Learning algorithm trained on Sentinel-2 and auxiliary TanDEM-X topographic data for automated mapping of Antarctic supraglacial lakes. To ensure the spatio-temporal transferability of our method, a Random Forest was trained on 14 training regions and applied over eight spatially independent test regions distributed across the whole Antarctic continent. In addition, we employed our workflow for large-scale application over Amery Ice Shelf where we calculated interannual supraglacial lake dynamics between 2017 and 2020 at full ice shelf coverage. To validate our supraglacial lake detection algorithm, we randomly created point samples over our classification results and compared them to Sentinel-2 imagery. The point comparisons were evaluated using a confusion matrix for calculation of selected accuracy metrics. Our analysis revealed wide-spread supraglacial lake occurrence in all three Antarctic regions. For the first time, we identified supraglacial meltwater features on Abbott, Hull and Cosgrove Ice Shelves in West Antarctica as well as for the entire Amery Ice Shelf for years 2017–2020. Over Amery Ice Shelf, maximum lake extent varied strongly between the years with the 2019 melt season characterized by the largest areal coverage of supraglacial lakes (~763 km2). The accuracy assessment over the test regions revealed an average Kappa coefficient of 0.86 where the largest value of Kappa reached 0.98 over George VI Ice Shelf. Future developments will involve the generation of circum-Antarctic supraglacial lake mapping products as well as their use for further methodological developments using Sentinel-1 SAR data in order to characterize intraannual supraglacial meltwater dynamics also during polar night and independent of meteorological conditions. In summary, the implementation of the Random Forest classifier enabled the development of the first automated mapping method applied to Sentinel-2 data distributed across all three Antarctic regions.

Glacial Lakes Mapping Using Multi Satellite PlanetScope Imagery and Deep Learning

“…Random Forest (RF) has been a popular classifier for the detection of glacial lakes in remote sensing imagery [56][57][58]. Therefore, to compare the performance of the CNN, RF Classifier was trained to classify PlanetScope images into water and background classes.…”

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

“…The study sites used for training and testing the implemented supraglacial lake detection algorithm are evenly distributed across the Antarctic continent (Figure 4) and were selected based on known supraglacial lake locations (e.g., [18,28,[44][45][46]), as described in Dirscherl et al [28]. To ensure the spatial as well as temporal transferability of our method, training and test sites were chosen to cover (1) all different types of environments and surface features occurring in Antarctica (e.g., bare ice, blue ice, slushy snow, wet snow, dry snow, supraglacial lakes, rock outcrop, and crevasse fields) and (2) various dates throughout austral summer (1 December to 1 March); thus, the melting season of a given year allowing to include supraglacial lake features with varying appearances.…”

“…In detail, the selected training and test sites cover dates during the 2016/2017, 2017/2018, 2018/2019, and 2019/2020 summer seasons (see Figure 5). In agreement with their spatial location, these dates were chosen due to particularly strong surface melting during these years, e.g., over West Antarctica and the Antarctic Peninsula in January 2020 and over East Antarctica in January 2017 and 2019 (e.g., [28]). In total, eight of the Sentinel-1 training sites covered regions on the East Antarctic ice sheet (EAIS), two were located on the West Antarctic ice sheet (WAIS) and three on the API.…”

“…Next, Halberstadt et al [26] employed unsupervised k-means clustering on Landsat 8 scenes over two East Antarctic ice shelves to train a suite of supervised classifiers and Dell et al [24] advanced the "FAST" (Fully Automated Supraglacial lake area and volume Tracking) algorithm [27] to automatically track supraglacial lakes in Landsat 8 and Sentinel-2 imagery over Nivlisen Ice Shelf, East Antarctica. Finally, our companion paper [28] presented an automated Sentinel-2 supraglacial lake classification algorithm developed on basis of a random forest (RF) classifier and was tested on spatially and temporally independent acquisitions distributed across the Antarctic continent. While these studies rely on the use of optical multi-spectral data, synthetic aperture radar (SAR) data are currently used for mainly visual interpretation and evaluation of Antarctic supraglacial lakes (e.g., [22,29]).…”

Monitoring Large-Scale Inland Water Dynamics by Fusing Sentinel-1 SAR and Sentinel-3 Altimetry Data and by Analyzing Causal Effects of Snowmelt

“…Therefore, they are inevitably affected by cloud cover and polar darkness, which frequently happen for alpine regions and high-latitude zones [9]. Moreover, the spectral feature of water in the multi-spectral sensor is also affected by the variation of atmospheric/illumination conditions and water dynamics, such as water depth, sediment load, eutrophication degree, turbidity, sun angle, and sensor view angle [15,16]. On the contrary, SAR data can be utilized for waterbody monitoring thanks to its cloud-penetrating applicability and illumination-independent characteristics.…”