Next Article in Journal
Editorial for Special Issue “High Resolution Active Optical Remote Sensing Observations of Aerosols, Clouds and Aerosol–Cloud Interactions and Their Implication to Climate”
Next Article in Special Issue
Assessment of the Stability of Passive Microwave Brightness Temperatures for NASA Team Sea Ice Concentration Retrievals
Previous Article in Journal
Maximizing Temporal Correlations in Long-Term Global Satellite Soil Moisture Data-Merging
Previous Article in Special Issue
A New Algorithm for Daily Sea Ice Lead Identification in the Arctic and Antarctic Winter from Thermal-Infrared Satellite Imagery
Open AccessArticle

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

1
École Nationale des Sciences Géographiques, Univ. Gustave Eiffel, 77455 Marne-la-Vallée, France
2
Nansen Environmental and Remote Sensing Center, 5006 Bergen, Norway
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(13), 2165; https://doi.org/10.3390/rs12132165
Received: 17 May 2020 / Revised: 26 June 2020 / Accepted: 30 June 2020 / Published: 7 July 2020
(This article belongs to the Special Issue Polar Sea Ice: Detection, Monitoring and Modeling)
A new algorithm for classification of sea ice types on Sentinel-1 Synthetic Aperture Radar (SAR) data using a convolutional neural network (CNN) is presented. The CNN is trained on reference ice charts produced by human experts and compared with an existing machine learning algorithm based on texture features and random forest classifier. The CNN is trained on two datasets in 2018 and 2020 for retrieval of four classes: ice free, young ice, first-year ice and old ice. The accuracy of our classification is 90.5% for the 2018-dataset and 91.6% for the 2020-dataset. The uncertainty is a bit higher for young ice (85%/76% accuracy in 2018/2020) and first-year ice (86%/84% accuracy in 2018/2020). Our algorithm outperforms the existing random forest product for each ice type. It has also proved to be more efficient in computing time and less sensitive to the noise in SAR data. The code is publicly available. View Full-Text
Keywords: convolutional neural network; Sentinel-1; SAR; sea ice type; ice chart; Arctic convolutional neural network; Sentinel-1; SAR; sea ice type; ice chart; Arctic
Show Figures

Graphical abstract

MDPI and ACS Style

Boulze, H.; Korosov, A.; Brajard, J. Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks. Remote Sens. 2020, 12, 2165. https://doi.org/10.3390/rs12132165

AMA Style

Boulze H, Korosov A, Brajard J. Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks. Remote Sensing. 2020; 12(13):2165. https://doi.org/10.3390/rs12132165

Chicago/Turabian Style

Boulze, Hugo; Korosov, Anton; Brajard, Julien. 2020. "Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks" Remote Sens. 12, no. 13: 2165. https://doi.org/10.3390/rs12132165

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
Search more from Scilit
 
Search
Back to TopTop