Articles | Volume 15, issue 11
The Cryosphere, 15, 5041–5059, 2021
https://doi.org/10.5194/tc-15-5041-2021
The Cryosphere, 15, 5041–5059, 2021
https://doi.org/10.5194/tc-15-5041-2021

Research article 01 Nov 2021

Research article | 01 Nov 2021

Image classification of marine-terminating outlet glaciers in Greenland using deep learning methods

Melanie Marochov et al.

Data sets

Sentinel-2 imagery Copernicus Open Access Hub https://scihub.copernicus.eu/dhus/#/home

Model code and software

SEE_ICE: Glacial landscape classification with deep learning Patrice Carbonneau and Melanie Marochov http://doi.org/10.5281/zenodo.4081095

CNN-Supervised-Classification (1.1) Patrice Carbonneau and James Dietrich https://doi.org/10.5281/zenodo.3928808

Download
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.