Next Article in Journal
Quality Analysis of Direct Georeferencing in Aspects of Absolute Accuracy and Precision for a UAV-Based Laser Scanning System
Previous Article in Journal
Encoding Spectral-Spatial Features for Hyperspectral Image Classification in the Satellite Internet of Things System
Previous Article in Special Issue
A Blended Sea Ice Concentration Product from AMSR2 and VIIRS
 
 
Article

Fine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs

1
Department of Ecology & Evolution, Stony Brook University, Stony Brook, NY 11790, USA
2
Institute for Advanced Computational Science, Stony Brook University, Stony Brook, NY 11794, USA
*
Author to whom correspondence should be addressed.
Academic Editors: Mohammed Shokr and Yufang Ye
Remote Sens. 2021, 13(18), 3562; https://doi.org/10.3390/rs13183562
Received: 5 July 2021 / Revised: 15 August 2021 / Accepted: 29 August 2021 / Published: 8 September 2021
(This article belongs to the Special Issue Polar Sea Ice: Detection, Monitoring and Modeling)
Fine-scale sea ice conditions are key to our efforts to understand and model climate change. We propose the first deep learning pipeline to extract fine-scale sea ice layers from high-resolution satellite imagery (Worldview-3). Extracting sea ice from imagery is often challenging due to the potentially complex texture from older ice floes (i.e., floating chunks of sea ice) and surrounding slush ice, making ice floes less distinctive from the surrounding water. We propose a pipeline using a U-Net variant with a Resnet encoder to retrieve ice floe pixel masks from very-high-resolution multispectral satellite imagery. Even with a modest-sized hand-labeled training set and the most basic hyperparameter choices, our CNN-based approach attains an out-of-sample F1 score of 0.698–a nearly 60% improvement when compared to a watershed segmentation baseline. We then supplement our training set with a much larger sample of images weak-labeled by a watershed segmentation algorithm. To ensure watershed derived pack-ice masks were a good representation of the underlying images, we created a synthetic version for each weak-labeled image, where areas outside the mask are replaced by open water scenery. Adding our synthetic image dataset, obtained at minimal effort when compared with hand-labeling, further improves the out-of-sample F1 score to 0.734. Finally, we use an ensemble of four test metrics and evaluated after mosaicing outputs for entire scenes to mimic production setting during model selection, reaching an out-of-sample F1 score of 0.753. Our fully-automated pipeline is capable of detecting, monitoring, and segmenting ice floes at a very fine level of detail, and provides a roadmap for other use-cases where partial results can be obtained with threshold-based methods but a context-robust segmentation pipeline is desired. View Full-Text
Keywords: pack-ice; worldview 3; semantic segmentation; deep learning; remote sensing image processing pack-ice; worldview 3; semantic segmentation; deep learning; remote sensing image processing
Show Figures

Graphical abstract

MDPI and ACS Style

Gonçalves, B.C.; Lynch, H.J. Fine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs. Remote Sens. 2021, 13, 3562. https://doi.org/10.3390/rs13183562

AMA Style

Gonçalves BC, Lynch HJ. Fine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs. Remote Sensing. 2021; 13(18):3562. https://doi.org/10.3390/rs13183562

Chicago/Turabian Style

Gonçalves, Bento C., and Heather J. Lynch. 2021. "Fine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs" Remote Sensing 13, no. 18: 3562. https://doi.org/10.3390/rs13183562

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop