Extracting Glacier Calving Fronts by Deep Learning: The Benefit of Multispectral, Topographic, and Textural Input Features

Loebel, Erik; Scheinert, Mirko; Horwath, Martin; Heidler, Konrad; Christmann, Julia; Phan, Long Duc; Humbert, Angelika; Zhu, Xiao Xiang

doi:10.1109/tgrs.2022.3208454

Cited by 17 publications

(18 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many methods are based on the U-Net (Ronneberger et al, 2015). One approach is to segment the images into different areas and extract the calving front as the border between segmentation areas (Hartmann et al, 2021;Zhang et al, 2019;Baumhoer et al, 2019;Periyasamy et al, 2022;Loebel et al, 2022). Another approach directly trains a model on the position of the calving front (Davari et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

Out-of-the-box calving front detection method using deep-learning

Herrmann¹,

Gourmelon²,

Seehaus³

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Glaciers across the globe react to the changing climate. Monitoring the transformation of glaciers is essential for projecting their contribution to global mean sea level (GMSL) rise. The delineation of glacier-calving fronts is an important part of the satellite-based monitoring process. This work presents a calving front extraction method based on the deep learning framework nnU-Net, which stands for no new U-Net. The framework automates the training of a popular neural network, called U-Net, designed for segmentation tasks. Our presented method marks the calving front in Synthetic Aperture Radar images of glaciers. The images are taken by six different sensor systems. A benchmark dataset for calving front extraction is used for training and evaluation. The dataset contains two labels for each image. One label denotes a classic image segmentation into different zones (glacier, ocean, rock, and no information available). The other label marks the edge between the glacier and the ocean, i. e., the calving front. In this work, the nnU-Net is modified to predict both labels simultaneously. In the field of machine learning, the prediction of multiple labels is referred to as Multi-Task-Learning (MTL). The resulting predictions of both labels benefit from simultaneous optimization. For further testing of the capabilities of MTL, two different network architectures are compared, and an additional task, the segmentation of the glacier outline, is added to the training. In the end, we show that fusing the label of the calving front and the zone label is the most efficient way to optimize both tasks with no significant accuracy reduction compared to the MTL neural network architectures. The automatic detection of the calving front with a nnU-Net trained on fused labels improves from the baseline mean distance error of 753 ± 76 m to 541 ± 84 m. The scripts for our experiments are published on Gitlab (https://gitlab.cs.fau.de/ho11laqe/nnunet\\_glacer.git).

show abstract

Section: Related Workmentioning

confidence: 99%

Out-of-the-box calving front detection method using deep-learning

Herrmann¹,

Gourmelon²,

Seehaus³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…time series generation. Deep neural networks demonstrated their superior performance for calving front detection in several studies in means of speed and still achieve accuracies better or comparable to manual delineations [21][22][23][29][30][31] . Nevertheless, occasional failures occur where incorrect front positions are extracted due to icebergs, mélange, surface melt or cloud cover.…”

Section: Post-processingmentioning

confidence: 99%

“…IceLines is validated by calculating the distance difference between the automatically extracted daily fronts and manual front delineations. This is a commonly applied method to assess the accuracy of the derived front positions 21,23,31 . Nevertheless, manual front delineation is a very challenging task and underlies a high degree of subjectivity.…”

Section: Technical Validationmentioning

confidence: 99%

IceLines – A new data set of Antarctic ice shelf front positions

et al. 2023

Self Cite

View full text Add to dashboard Cite

The frontal position of an ice shelf is an important parameter for ice dynamic modelling, the computation of mass fluxes, mapping glacier area change, calculating iceberg production rates and the estimation of ice discharge to the ocean. Until now, continuous and up-to-date information on Antarctic calving front locations is scarce due to the time-consuming manual delineation of fronts and the previously limited amount of suitable earth observation data. Here, we present IceLines, a novel data set on Antarctic ice shelf front positions to assess calving front change at an unprecedented temporal and spatial resolution. More than 19,400 calving front positions were automatically extracted creating dense inter- and intra-annual time series of calving front change for the era of Sentinel-1 (2014-today). The calving front time series can be accessed via the EOC GeoService hosted by DLR and is updated on a monthly basis. For the first time, the presented IceLines data set provides the possibility to easily include calving front dynamics in scientific studies and modelling to improve our understanding about ice sheet dynamics.

show abstract

“…Further progress in this field was made by extending the UNet model or exploiting the advances of more recent segmentation model architectures. For example, Loebel et al [13] add more layers and thereby increase the number of down-and upsampling steps. This enlarges the spatial context that the network can consider for its decisions and therefore leads to better predictions.…”

Section: A Detecting Calving Fronts In the Deep Learning Eramentioning

confidence: 99%

“…In order to thoroughly evaluate our model and compare it with other approaches, we choose two large-scale datasets of marine-terminating glaciers in Greenland for training and evaluation purposes, namely the CALFIN dataset [4] and the calving front dataset from TU Dresden (TUD) [13]. Both of these datasets include respective testing data.…”

Section: A Datasetsmentioning

confidence: 99%

Deep Active Contour Models for Delineating Glacier Calving Fronts

Heidler

Mou

Loebel

et al. 2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

This work has been accepted by IEEE TGRS for publication in a future issue. Choosing how to encode a realworld problem as a machine learning task is an important design decision in machine learning. The task of glacier calving front modeling has often been approached as a semantic segmentation task. Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called "Charting Outlines by Recurrent Adaptation" (COBRA), combines Convolutional Neural Networks (CNNs) for feature extraction and active contour models for the delineation. By training and evaluating on several large-scale datasets of Greenland's outlet glaciers, we show that this approach indeed outperforms the aforementioned methods based on segmentation and edgedetection. Finally, we demonstrate that explicit contour detection has benefits over pixel-wise methods when quantifying the models' prediction uncertainties.The project page containing the code and animated model predictions can be found at https://khdlr.github.io/COBRA/.

show abstract

Extracting Glacier Calving Fronts by Deep Learning: The Benefit of Multispectral, Topographic, and Textural Input Features

Cited by 17 publications

References 47 publications

Out-of-the-box calving front detection method using deep-learning

Out-of-the-box calving front detection method using deep-learning

IceLines – A new data set of Antarctic ice shelf front positions

Deep Active Contour Models for Delineating Glacier Calving Fronts

Contact Info

Product

Resources

About