A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery
Arctic sea ice has a significant effect on global climate change, ship navigation, Arctic ecosystems, and human activities. Therefore, it is essential to produce high-resolution sea ice maps that accurately represent the geographical distribution of various sea ice types. Based on deep learning tech...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/277 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587579119108096 |
|---|---|
| author | Li Zhao Yufeng Zhou Wei Zhong Cheng Jin Bo Liu Fangzhao Li |
| author_facet | Li Zhao Yufeng Zhou Wei Zhong Cheng Jin Bo Liu Fangzhao Li |
| author_sort | Li Zhao |
| collection | DOAJ |
| description | Arctic sea ice has a significant effect on global climate change, ship navigation, Arctic ecosystems, and human activities. Therefore, it is essential to produce high-resolution sea ice maps that accurately represent the geographical distribution of various sea ice types. Based on deep learning technology, many automatic sea ice classification algorithms have been developed using synthetic aperture radar (SAR) imagery over the last decade. However, sea ice classification faces two vital challenges: (1) it is difficult to distinguish sea ice types with close developmental stages solely from SAR images and (2) an imbalanced sea ice dataset has a significantly negative effect on ice classification model performance. In this article, a spatio-temporal deep learning model—the Dynamic Multi-Layer Perceptron (MLP)—is utilized to classify 10 sea ice types automatically. It consists of a SAR image branch and a spatio-temporal branch, which extracts SAR image features and spatio-temporal distribution characteristics of sea ice, respectively. By projecting similar image features to different positions in the spatio-temporal feature space dynamically, the Dynamic MLP model effectively distinguishes between similar sea ice types. Furthermore, to reduce the impact of data imbalance on model performance, the dynamic curriculum learning (DCL) method is used to train the Dynamic MLP model. Experimental results demonstrate that our proposed method outperforms the long short-term memory (LSTM) network approach in distinguishing between sea ice types with similar developmental stages. Moreover, the DCL training method can also effectively improve model performance in identifying minority ice types. |
| format | Article |
| id | doaj-art-7f57d254f9e44ef399184e9af81aae57 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-7f57d254f9e44ef399184e9af81aae572025-01-24T13:47:58ZengMDPI AGRemote Sensing2072-42922025-01-0117227710.3390/rs17020277A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR ImageryLi Zhao0Yufeng Zhou1Wei Zhong2Cheng Jin3Bo Liu4Fangzhao Li5College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaKey Laboratory of Smart Earth, Beijing 100029, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaKey Laboratory of Smart Earth, Beijing 100029, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaArctic sea ice has a significant effect on global climate change, ship navigation, Arctic ecosystems, and human activities. Therefore, it is essential to produce high-resolution sea ice maps that accurately represent the geographical distribution of various sea ice types. Based on deep learning technology, many automatic sea ice classification algorithms have been developed using synthetic aperture radar (SAR) imagery over the last decade. However, sea ice classification faces two vital challenges: (1) it is difficult to distinguish sea ice types with close developmental stages solely from SAR images and (2) an imbalanced sea ice dataset has a significantly negative effect on ice classification model performance. In this article, a spatio-temporal deep learning model—the Dynamic Multi-Layer Perceptron (MLP)—is utilized to classify 10 sea ice types automatically. It consists of a SAR image branch and a spatio-temporal branch, which extracts SAR image features and spatio-temporal distribution characteristics of sea ice, respectively. By projecting similar image features to different positions in the spatio-temporal feature space dynamically, the Dynamic MLP model effectively distinguishes between similar sea ice types. Furthermore, to reduce the impact of data imbalance on model performance, the dynamic curriculum learning (DCL) method is used to train the Dynamic MLP model. Experimental results demonstrate that our proposed method outperforms the long short-term memory (LSTM) network approach in distinguishing between sea ice types with similar developmental stages. Moreover, the DCL training method can also effectively improve model performance in identifying minority ice types.https://www.mdpi.com/2072-4292/17/2/277Arctic sea ice classificationdeep learningsynthetic aperture radar (SAR)Sentinel-1 |
| spellingShingle | Li Zhao Yufeng Zhou Wei Zhong Cheng Jin Bo Liu Fangzhao Li A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery Remote Sensing Arctic sea ice classification deep learning synthetic aperture radar (SAR) Sentinel-1 |
| title | A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery |
| title_full | A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery |
| title_fullStr | A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery |
| title_full_unstemmed | A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery |
| title_short | A Spatio-Temporal Deep Learning Model for Automatic Arctic Sea Ice Classification with Sentinel-1 SAR Imagery |
| title_sort | spatio temporal deep learning model for automatic arctic sea ice classification with sentinel 1 sar imagery |
| topic | Arctic sea ice classification deep learning synthetic aperture radar (SAR) Sentinel-1 |
| url | https://www.mdpi.com/2072-4292/17/2/277 |
| work_keys_str_mv | AT lizhao aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT yufengzhou aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT weizhong aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT chengjin aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT boliu aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT fangzhaoli aspatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT lizhao spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT yufengzhou spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT weizhong spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT chengjin spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT boliu spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery AT fangzhaoli spatiotemporaldeeplearningmodelforautomaticarcticseaiceclassificationwithsentinel1sarimagery |