Next Article in Journal
Spatiotemporal Changes of Winter Wheat Planted and Harvested Areas, Photosynthesis and Grain Production in the Contiguous United States from 2008–2018
Previous Article in Journal
The Use of Superspheroids as Surrogates for Modeling Electromagnetic Wave Scattering by Ice Crystals
Article

Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks

1
Department of Science and Technology, UiT the Arctic University of Norway, NO-9037 Tromsø, Norway
2
Norwegian Ice Service, Norwegian Meteorological Institute, P.O. Box 6314 Langnes, NO-9293 Tromsø, Norway
*
Author to whom correspondence should be addressed.
Academic Editor: John Paden
Remote Sens. 2021, 13(9), 1734; https://doi.org/10.3390/rs13091734
Received: 1 March 2021 / Revised: 21 April 2021 / Accepted: 22 April 2021 / Published: 29 April 2021
(This article belongs to the Special Issue Machine Learning Methods for Polar Regions)
We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results. View Full-Text
Keywords: convolutional neural network; ice edge detection; polar region; Sentinel-1; sea ice classification; synthetic aperture radar convolutional neural network; ice edge detection; polar region; Sentinel-1; sea ice classification; synthetic aperture radar
Show Figures

Figure 1

MDPI and ACS Style

Khaleghian, S.; Ullah, H.; Kræmer, T.; Hughes, N.; Eltoft, T.; Marinoni, A. Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks. Remote Sens. 2021, 13, 1734. https://doi.org/10.3390/rs13091734

AMA Style

Khaleghian S, Ullah H, Kræmer T, Hughes N, Eltoft T, Marinoni A. Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks. Remote Sensing. 2021; 13(9):1734. https://doi.org/10.3390/rs13091734

Chicago/Turabian Style

Khaleghian, Salman, Habib Ullah, Thomas Kræmer, Nick Hughes, Torbjørn Eltoft, and Andrea Marinoni. 2021. "Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks" Remote Sensing 13, no. 9: 1734. https://doi.org/10.3390/rs13091734

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