18 Nov 2020

18 Nov 2020

Review status: this preprint is currently under review for the journal TC.

Image Classification of Marine-Terminating Outlet Glaciers using Deep Learning Methods

Melanie Marochov, Chris R. Stokes, and Patrice E. Carbonneau Melanie Marochov et al.
  • Department of Geography, Durham University, Durham, DH1 3LE, UK

Abstract. A wealth of research has focused on elucidating the key controls on mass loss from the Greenland and Antarctic ice sheets in response to climate forcing, specifically in relation to the drivers of marine-terminating outlet glacier change. Despite the burgeoning availability of medium resolution satellite data, the manual methods traditionally used to monitor change in satellite imagery of marine-terminating outlet glaciers are time-consuming and can be subjective, especially where mélange exists at the terminus. Recent advances in deep learning applied to image processing have created a new frontier in the field of automated delineation of glacier termini. However, at this stage, there remains a paucity of research on the use of deep learning for pixel-level semantic image classification of outlet glacier environments. In this contribution, we apply and test a two-phase deep learning approach based on a well-established convolutional neural network (CNN) called VGG16 for automated classification of Sentinel-2 satellite images. The novel workflow, termed CNN-Supervised Classification (CSC), was originally developed for fluvial settings but is adapted here to produce multi-class outputs for test imagery of glacial environments containing marine-terminating outlet glaciers in eastern Greenland. Results show mean F1 scores up to 95 % for in-sample test imagery and 93 % for out-of-sample test imagery, establishing a state-of-the-art in classification of marine-terminating glacial environments with significant improvements over traditional pixel-based methods such as band ratio techniques. This demonstrates the transferability and robustness of the deep learning workflow for automated classification despite the complex and seasonally variable characteristics of the imagery. Future research could focus on the integration of deep learning classification workflows with platforms such as Google Earth Engine, to more efficiently classify imagery and produce datasets for a range of glacial applications without the need for substantial prior experience in coding or deep learning.

Melanie Marochov et al.

Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for authors/editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Melanie Marochov et al.

Data sets

Image Classification of Marine-Terminating Outlet Glaciers using Deep Learning Methods: Pre-trained Models [dataset] Melanie Marochov and Patrice Carbonneau

Model code and software

SEE_ICE: Glacial Landscape Classification with Deep Learning Patrice Carbonneau and Melanie Marochov

Melanie Marochov et al.


Total article views: 578 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
374 202 2 578 36 5 3
  • HTML: 374
  • PDF: 202
  • XML: 2
  • Total: 578
  • Supplement: 36
  • BibTeX: 5
  • EndNote: 3
Views and downloads (calculated since 18 Nov 2020)
Cumulative views and downloads (calculated since 18 Nov 2020)

Viewed (geographical distribution)

Total article views: 530 (including HTML, PDF, and XML) Thereof 523 with geography defined and 7 with unknown origin.
Country # Views %
  • 1
Latest update: 07 Mar 2021
Short summary
Research into the use of deep learning for pixel-level classification of landscapes containing marine-terminating glaciers is lacking. We adapt a novel and transferable deep learning workflow to classify satellite imagery containing marine-terminating outlet glaciers in Greenland. Our workflow achieves high accuracy and mimics human visual performance, potentially providing a useful tool to monitor glacier change and further understand the impacts of climate change in complex glacial settings.