Antarctic Supraglacial Lake Identification Using Landsat-8 Image Classification

Anna Ruth W Halberstadt,Colin J Gleason,Allen Pope,Mahsa S Moussavi,Luke D Trusel,Robert M Deconto

doi:10.3390/rs12081327

Abstract

Surface meltwater generated on ice shelves fringing the Antarctic Ice Sheet can drive ice-shelf collapse, leading to ice sheet mass loss and contributing to global sea level rise. A quantitative assessment of supraglacial lake evolution is required to understand the influence of Antarctic surface meltwater on ice-sheet and ice-shelf stability. Cloud computing platforms have made the required remote sensing analysis computationally trivial, yet a careful evaluation of image processing techniques for pan-Antarctic lake mapping has yet to be performed. This work paves the way for automating lake identification at a continental scale throughout the satellite observational record via a thorough methodological analysis. We deploy a suite of different trained supervised classifiers to map and quantify supraglacial lake areas from multispectral Landsat-8 scenes, using training data generated via manual interpretation of the results from k-means clustering. Best results are obtained using training datasets that comprise spectrally diverse unsupervised clusters from multiple regions and that include rock and cloud shadow classes. We successfully apply our trained supervised classifiers across two ice shelves with different supraglacial lake characteristics above a threshold sun elevation of 20°, achieving classification accuracies of over 90% when compared to manually generated validation datasets. The application of our trained classifiers produces a seasonal pattern of lake evolution. Cloud shadowed areas hinder large-scale application of our classifiers, as in previous work. Our results show that caution is required before deploying ‘off the shelf’ algorithms for lake mapping in Antarctica, and suggest that careful scrutiny of training data and desired output classes is essential for accurate results. Our supervised classification technique provides an alternative and independent method of lake identification to inform the development of a continent-wide supraglacial lake mapping product.

Highlights

Both the Greenland and Antarctic ice sheets are losing mass at an increasing rate (e.g., [1,2,3,4,5,6,7,8])
Mapping the extent and evolution of surface meltwater is crucial for understanding the role of supraglacial hydrology in Antarctic ice-sheet stability, and it provides important boundary conditions for assessing the stability of the Antarctic Ice Sheet
Our goals for this manuscript were to: (1) present a method for accurate lake identification that is broadly applicable in space and time and is robust for different ice environments; (2) assess the sensitivity of lake identification to training data and training classes; (3) assess the sensitivity of lake identification to classification algorithms; and (4) explore the transferability of our classification scheme across two ice shelf locations

Summary

Introduction

Both the Greenland and Antarctic ice sheets are losing mass at an increasing rate (e.g., [1,2,3,4,5,6,7,8]). The Greenland Ice Sheet is projected to contribute up to ~25 cm of global mean sea level by the year 2100 under ’worst case’ greenhouse-gas emissions scenarios [9]. Mass loss from the Antarctic Ice Sheet has the potential to raise global mean sea level by tens of meters in future centuries (e.g., [10,11,12,13]) and is projected to dominate global sea level rise in the near future [14,15]. Surface meltwater plays a central role in ice sheet contributions to sea level through both direct surface meltwater runoff and indirect ice dynamical impacts. The influence of supraglacial hydrology on ice-sheet dynamics has been extensively explored for the Greenland Ice Sheet, where rapid drainage of surface lakes via hydrofracture to the ice-sheet bed during the early melt season and the development of perennial river networks that drain into moulins during the mid to late season influence subglacial effective pressures and ice flow velocities on short and longer timescales (e.g., [16,17,18,19,20,21,22,23,24,25,26,27,28])

Objectives

Methods

Results

Discussion

Conclusion