An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks
The distribution of sea ice is one of the major safety hazards for sea navigation. As human activities in polar regions become more frequent, monitoring and forecasting of sea ice are of great significance. In this paper, we use SAR data from the C-band synthetic aperture radar (SAR) Gaofen-3 satell...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14040906 https://doaj.org/article/5ece0160ae18489bad8d09618b875a98 |
id |
ftdoajarticles:oai:doaj.org/article:5ece0160ae18489bad8d09618b875a98 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:5ece0160ae18489bad8d09618b875a98 2023-05-15T15:01:50+02:00 An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks Jiande Zhang Wenyi Zhang Yuxin Hu Qingwei Chu Lei Liu 2022-02-01T00:00:00Z https://doi.org/10.3390/rs14040906 https://doaj.org/article/5ece0160ae18489bad8d09618b875a98 EN eng MDPI AG https://www.mdpi.com/2072-4292/14/4/906 https://doaj.org/toc/2072-4292 doi:10.3390/rs14040906 2072-4292 https://doaj.org/article/5ece0160ae18489bad8d09618b875a98 Remote Sensing, Vol 14, Iss 906, p 906 (2022) sea ice classification synthetic aperture radar Gaofen-3 convolutional neural networks multiscale feature fusion Science Q article 2022 ftdoajarticles https://doi.org/10.3390/rs14040906 2022-12-31T00:55:46Z The distribution of sea ice is one of the major safety hazards for sea navigation. As human activities in polar regions become more frequent, monitoring and forecasting of sea ice are of great significance. In this paper, we use SAR data from the C-band synthetic aperture radar (SAR) Gaofen-3 satellite in the dual-polarization (VV, VH) fine strip II (FSII) mode of operation to study the Arctic sea ice classification in winter. SAR data we use were taken in the western Arctic Ocean from January to February 2020. We classify the sea ice into four categories, namely new ice (NI), thin first-year ice (tI), thick first-year ice (TI), and old ice (OI), by referring to the ice maps provided by the Canadian Ice Service (CIS). Then, we use the deep learning model MobileNetV3 as the backbone network, input samples of different sizes, and combine the backbone network with multiscale feature fusion methods to build a deep learning model called Multiscale MobileNet (MSMN). Dual-polarization SAR data are used to synthesize pseudocolor images and produce samples of sizes 16 × 16 × 3, 32 × 32 × 3, and 64 × 64 × 3 as input. Ultimately, MSMN can reach over 95% classification accuracy on testing SAR sea ice images. The classification results using only VV polarization or VH polarization data are tested, and it is found that using dual-polarization data could improve the classification accuracy by 10.05% and 9.35%, respectively. When other classification models are trained using the training data from this paper for comparison, the accuracy of MSMN is 4.86% and 1.84% higher on average than that of the model built using convolutional neural networks (CNNs) and ResNet18 model, respectively. Article in Journal/Newspaper Arctic Arctic Ocean Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Arctic Ocean Remote Sensing 14 4 906 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
sea ice classification synthetic aperture radar Gaofen-3 convolutional neural networks multiscale feature fusion Science Q |
spellingShingle |
sea ice classification synthetic aperture radar Gaofen-3 convolutional neural networks multiscale feature fusion Science Q Jiande Zhang Wenyi Zhang Yuxin Hu Qingwei Chu Lei Liu An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
topic_facet |
sea ice classification synthetic aperture radar Gaofen-3 convolutional neural networks multiscale feature fusion Science Q |
description |
The distribution of sea ice is one of the major safety hazards for sea navigation. As human activities in polar regions become more frequent, monitoring and forecasting of sea ice are of great significance. In this paper, we use SAR data from the C-band synthetic aperture radar (SAR) Gaofen-3 satellite in the dual-polarization (VV, VH) fine strip II (FSII) mode of operation to study the Arctic sea ice classification in winter. SAR data we use were taken in the western Arctic Ocean from January to February 2020. We classify the sea ice into four categories, namely new ice (NI), thin first-year ice (tI), thick first-year ice (TI), and old ice (OI), by referring to the ice maps provided by the Canadian Ice Service (CIS). Then, we use the deep learning model MobileNetV3 as the backbone network, input samples of different sizes, and combine the backbone network with multiscale feature fusion methods to build a deep learning model called Multiscale MobileNet (MSMN). Dual-polarization SAR data are used to synthesize pseudocolor images and produce samples of sizes 16 × 16 × 3, 32 × 32 × 3, and 64 × 64 × 3 as input. Ultimately, MSMN can reach over 95% classification accuracy on testing SAR sea ice images. The classification results using only VV polarization or VH polarization data are tested, and it is found that using dual-polarization data could improve the classification accuracy by 10.05% and 9.35%, respectively. When other classification models are trained using the training data from this paper for comparison, the accuracy of MSMN is 4.86% and 1.84% higher on average than that of the model built using convolutional neural networks (CNNs) and ResNet18 model, respectively. |
format |
Article in Journal/Newspaper |
author |
Jiande Zhang Wenyi Zhang Yuxin Hu Qingwei Chu Lei Liu |
author_facet |
Jiande Zhang Wenyi Zhang Yuxin Hu Qingwei Chu Lei Liu |
author_sort |
Jiande Zhang |
title |
An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
title_short |
An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
title_full |
An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
title_fullStr |
An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
title_full_unstemmed |
An Improved Sea Ice Classification Algorithm with Gaofen-3 Dual-Polarization SAR Data Based on Deep Convolutional Neural Networks |
title_sort |
improved sea ice classification algorithm with gaofen-3 dual-polarization sar data based on deep convolutional neural networks |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14040906 https://doaj.org/article/5ece0160ae18489bad8d09618b875a98 |
geographic |
Arctic Arctic Ocean |
geographic_facet |
Arctic Arctic Ocean |
genre |
Arctic Arctic Ocean Sea ice |
genre_facet |
Arctic Arctic Ocean Sea ice |
op_source |
Remote Sensing, Vol 14, Iss 906, p 906 (2022) |
op_relation |
https://www.mdpi.com/2072-4292/14/4/906 https://doaj.org/toc/2072-4292 doi:10.3390/rs14040906 2072-4292 https://doaj.org/article/5ece0160ae18489bad8d09618b875a98 |
op_doi |
https://doi.org/10.3390/rs14040906 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
4 |
container_start_page |
906 |
_version_ |
1766333831000883200 |