the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Out-of-the-box calving front detection method using deep-learning
Nora Gourmelon
Thorsten Seehaus
Andreas Maier
Johannes Fürst
Matthias Holger Braun
Vincent Christlein
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).
- Preprint
(29881 KB) - Metadata XML
- BibTeX
- EndNote
Oskar Herrmann et al.
Status: final response (author comments only)
-
RC1: 'Comment on tc-2023-34', Anonymous Referee #1, 06 Apr 2023
- AC1: 'Reply on RC1', Oskar Herrmann, 31 May 2023
-
RC2: 'Comment on tc-2023-34', Anonymous Referee #2, 11 Apr 2023
General Comments:
This study applied nnU-Net by Isensee et al. (2021) to a benchmark dataset from Gourmelon et al. (2022). The author designed six experiments and showed that multi-task learning benefits each task’s performance, while there is no distinct difference between early- and late-branching, and adding the task of delineating the glacier boundary does not further improve the terminus delineation. The experimental design and results presented in this manuscript might be of more interest to the deep-learning community than to glaciologists, as the errors in glacier terminus delineation produced by this study are relatively large compared to other studies (Zhang et al., 2019; Cheng et al., 2021; Baumhoer et al., 2019). These termini may not be suitable for scientific research on ice-ocean interactions due to their relatively large error. Providing more termini that are beyond the benchmark dataset with lower error might be more beneficial to the glaciology community, but I understand it might be out of the scope of this study. Also, further details on technical aspects would be appreciated.
Major comments:
- The author applies a nnU-Net and improves the error from 753 ± 76 m by Gourmelon et al. (2022) to 541 ± 84 m. Still, 541 meters is a relatively large error for terminus delineation, compared with previous studies that have errors ranging from 33 to 108 meters (Zhang et al., 2019; Cheng et al., 2021; Baumhoer et al., 2019). Given the relatively large margin of error in the terminus products produced by this method, it might be challenging to conduct scientific research that relies on them. Also, providing more termini that go beyond the benchmark dataset might be more beneficial to the glaciology community, but I understand it might be out of the scope of this study.
- One key advantage of using no new U-Net is that the framework can take the fingerprint of the dataset and automatically configures the framework (adjust the hyperparameters). However, it is not clear to me which hyperparameters are being adjusted automatically, how they are adjusted, and what is the final choice of these hyperparameters. If we adopt the hyperparameters from nnU-Net and apply them to standard U-Net, would there be no difference between nnU-Net and U-Net? If that is the case, I suppose it is important to clearly demonstrate how to automatically adjust the hyperparameters and how these newly derived hyperparameters improve the results.
- While the author emphasizes that the method is an out-of-the-box application, it would be beneficial for the readers to have a clearer understanding of the steps taken by the author to ensure its out-of-the-box applicability. Providing further details on this aspect could enhance the credibility of the method's out-of-the-box applicability claim and contribute to its broader adoption in the research community.
Specific Comments:
Line 16: The scripts are not publicly available. As the author emphasizes that the method is out-of-the-box, it would be more beneficial if the codes are publicly available.
Line 66: What is the visual preparation? Why is the visual preparation necessary as the dataset from Gourmelon et al. (2022) is a benchmark dataset?
Line 115: Are sentences about the labels here and the sentences on Line 50 repeated?
Figure 3: For Crane, what is the black dots in the middle of the ocean?
Line 120: Are there any procedures to deal with the imbalance? It might be helpful to increase the weight of the positive pixel loss in the loss function.
Figure 5: Please explain the abbreviations of the glacier names.
Section 4.1: Additional information about the method needs to be provided. It would be beneficial to include more details on the data fingerprint and how to use the fingerprint to determine the hyperparameters in this study. The following are some specific descriptions that is unclear to me:
- What is the definition of the distribution of spacing?
- How to use the distribution of spacing to determine the annotation, image resampling strategy, and target spacing?
- Is the annotation equivalent to labeling the images? If so, how is that related to the distribution of the spacing?
- What is the image resampling strategy that is used?
- Is CT or z-score normalization used in this study? How to conduct the z-score normalization with image mean and standard deviation?
Line 175: Please be more clear about the minor changes here.
Lien 180: What is the post-processing step for the fifth experiment? How to combine the three types of output to get a single glacier terminus?
Line 188: “To generate a prediction of the zones, pixels classified as front are assigned to the ocean, and the glacier zone is dilated once with a 7x7 kernel.” Do the zones here represent the segmentation zone? If so, how does this lead to a glacier terminus? Similar to the fifth experiment, how to combine the two types of output to get a single glacier terminus?
Line 219: Why the errors of the STL approaches here are larger than the error of Gourmelon et al. (2022)?
Reference
Baumhoer, C. A., Dietz, A. J., Kneisel, C., and Kuenzer, C.: Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning, Remote Sensing, 11, 2529, https://doi.org/10.3390/rs11212529, 2019.
Cheng, D., Hayes, W., Larour, E., Mohajerani, Y., Wood, M., Velicogna, I., and Rignot, E.: Calving Front Machine (CALFIN): glacial termini dataset and automated deep learning extraction method for Greenland, 1972–2019, The Cryosphere, 15, 1663–1675, https://doi.org/10.5194/tc-15-1663-2021, 2021.
Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., and Maier-Hein, K. H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation, Nature Methods, 18, 203–211, https://doi.org/10.1038/s41592-020-01008-z, 2021.
Gourmelon, N., Seehaus, T., Braun, M., Maier, A., and Christlein, V.: Calving fronts and where to find them: a benchmark dataset and methodology for automatic glacier calving front extraction from synthetic aperture radar imagery, Earth System Science Data, 14, 4287– 4313, https://doi.org/10.5194/essd-14-4287-2022, 2022.
Zhang, E., Liu, L., and Huang, L.: Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach, The Cryosphere, 13, 1729–1741, https://doi.org/10.5194/tc-13-1729-2019, 2019.
Citation: https://doi.org/10.5194/tc-2023-34-RC2 - AC2: 'Reply on RC2', Oskar Herrmann, 31 May 2023
Oskar Herrmann et al.
Oskar Herrmann et al.
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
404 | 181 | 20 | 605 | 15 | 10 |
- HTML: 404
- PDF: 181
- XML: 20
- Total: 605
- BibTeX: 15
- EndNote: 10
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1