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

Abstract

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. 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 calving fronts. However, there remains a paucity of research on the use of deep learning for pixel-level semantic image classification of outlet glacier environments. Here, we apply and test a two-phase deep learning approach based on a well-established convolutional neural network (CNN) for automated classification of Sentinel-2 satellite imagery. The novel workflow, termed CNN-Supervised Classification (CSC) is adapted to produce multi-class outputs for unseen test imagery of glacial environments containing marine-terminating outlet glaciers in Greenland. Different CNN input parameters and training techniques are tested, with overall F1 scores for resulting classifications reaching up to 94 % for in-sample test data (Helheim Glacier) and 96 % for out-of-sample test data (Jakobshavn Isbrae and Store Glacier), establishing a state of the art in classification of marine-terminating glaciers in Greenland. Predicted calving fronts derived using optimal CSC input parameters have a mean deviation of 56.17 m (5.6 px) and median deviation of 24.7 m (2.5 px) from manually digitised fronts. This demonstrates the transferability and robustness of the deep learning workflow despite complex and seasonally variable imagery. Future research could focus on the integration of deep learning classification workflows with free cloud-based platforms, to efficiently classify imagery and produce datasets for a range of glacial applications without the need for substantial prior experience in coding or deep learning.

Calving fronts and where to find them: a benchmark dataset and methodology for automatic glacier calving front extraction from synthetic aperture radar imagery

“…While their code is open source, their dataset is not publicly available. A completely different approach to front delineation is taken by Marochov et al (2021). Instead of directly segmenting the entire images into the desired classes, Marochov et al (2021) use classification networks to determine the class of every single pixel in each image separately.…”

“…However, this approach is no longer feasible with the rapidly growing satellite image archives, as manual delineation is a highly time-consuming, tedious, and expensive task. Recent studies (Baumhoer et al, 2019;Cheng et al, 2021;Davari et al, 2022Davari et al, , 2021Hartmann et al, 2021;Heidler et al, 2021;Holzmann et al, 2021;Marochov et al, 2021;Mohajerani et al, 2019;Periyasamy et al, 2022;Zhang et al, 2019Zhang et al, , 2021 have focused on deep learning to extract the calving front and have shown great success. However, the evaluations of these studies have generally been based on different datasets and are, therefore, not comparable.…”

Long Time-Series Glacier Outlines in the Three-Rivers Headwater Region From 1986 to 2021 Based on Deep Learning

“…The non-glacial area (3.63×10 5 km 2 ) is far greater than the glacial area (2297.93 km 2 ) in the THR, so the positive and negative samples are extremely unbalanced, which has negative impacts on model performance [34]. To maintain the balance of positive and negative samples as much as possible, the sub-images without glacier were removed from the samples [35], [36] and were not used in the subsequent steps. In this study, a total of 692 SCGI sub-images were retained and used for the networks and were regarded as the ground truth.…”

Semantic Segmentation of Historical Photographs of the Antarctica Peninsula

“…An good example for semantic segmentation of the cryosphere with multiple classes can be found at Marochov et al (2021), in which CNNs are used for automated classification of Sentinel-2 satellite imagery in different classes. Due to the combination of RGB and near infrared data they can achieve an accuracy of over 90%.…”