Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model

Lichen GAO

doi:null

Your Location：

Home >

Browse articles >

Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model

Updated：2026-04-07

- Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model
- Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model
- 海洋湖沼学报(英文) 2026年页码：1-16
- Affiliations：
  
  Shandong University of Science and Technology, Qingdao 266590, China
- Author bio：
  
  2057178872@qq.com; 202211030704@sdust.edu.cn
- Funds：
- DOI：
  中图分类号：
- 收稿：2025-06-18，
  
  网络首发：2026-04-07，
- Accepted：
Scan QR Code
Lichen GAO. Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model[J/OL]. 海洋湖沼学报(英文), 2026,1-16.

GAO Lichen.Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model[J].Journal of Oceanology and Limnology,
Lichen GAO. Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model[J/OL]. 海洋湖沼学报(英文), 2026,1-16. DOI：

GAO Lichen.Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model[J].Journal of Oceanology and Limnology, DOI：.

摘要

Abstract

The satellite synthetic aperture radar (SAR) sensor is one of the most critical tools for monitoring Arctic sea ice. Classifying sea ice types based on SAR images has been a research hotspot. Most existing deep-learning-based sea ice classification models rely on the polarimetric information of SAR images while ignoring the gray-level co-occurrence matrix (GLCM) feature. This study develops a three-branch U-Net model for classifying sea ice in SAR images. By integrating polarimetric information

GLCM features

and auxiliary data

the model can classify open water (OW)

young ice (YIC)

first-year ice (FYI)

and old ice (OIC). The model is trained and tested on the well-known AI4Arctic sea ice challenge dataset. Experiments on 57 testing SAR images demonstrate that the proposed model achieves an overall classification accuracy of 91.45% and an Intersection over Union (IoU) of 0.846 4 for the four-type classification. Ablation experiments were conducted to evaluate the sensitivity of various GLCM features to sea ice classification. The effectiveness of the three-branch input for fusing polarimetric information

GLCM feature

and auxiliary data is validated. Results indicate that incorporating HV_mean significantly enhances classification performance

with an accuracy increase of approximately 0.7% and an improvement in IoU of 0.9%. The three-branch input structure is more effective than the single-branch structure in fusing three types of inputs

resulting in an accuracy increase of 4.7% and an improvement in IoU of 7%. Therefore

the proposed three-branch U-Net model demonstrates stable and reliable capabilities for classifying OW

YIC

FYI

and OIC in SAR images

providing a new approach for Arctic sea ice monitoring.

关键词

Keywords

references

Alkaee Taleghan S , Barrett A P , Meier W N et al . 2025 . IceBench: a benchmark for deep-learning-based sea-ice type classification . Remote Sensing , 17 ( 9 ): 1646 , https://doi.org/10.3390/rs17091646 https://doi.org/10.3390/rs17091646 .

Babb D G , Galley R J , Kirillov S et al . 2023 . The stepwise reduction of multiyear sea ice area in the arctic ocean since 1980 . Journal of Geophysical Research: Oceans , 128 ( 10 ): e2023 JC 020157 , https://doi.org/10.1029/2023JC020157 https://doi.org/10.1029/2023JC020157 .

Bi H B , Liang Y , Wang Y H et al . 2020 . Arctic multiyear sea ice variability observed from satellites: a review . Journal of Oceanology and Limnology , 38 ( 4 ): 962 - 984 , https://doi.org/10.1007/s00343-020-0093-7 https://doi.org/10.1007/s00343-020-0093-7 .

Chen X W , Patel M , Pena Cantu F J et al . 2024 . MMSeaIce: a collection of techniques for improving sea ice mapping with a multi-task model . The Cryosphere , 18 ( 4 ): 1621 - 1632 , https://doi.org/10.5194/tc-18-1621-2024 https://doi.org/10.5194/tc-18-1621-2024 .

Chen X W , Patel M , Xu L L et al . 2025 . A weakly supervised learning approach for sea ice stage of development classification from AI4 arctic sea ice challenge dataset. IEEE Transactions on Geoscience and Remote Sensing , 63 : 4202915 , https://doi.org/10.1109/TGRS.2025.3542803 https://doi.org/10.1109/TGRS.2025.3542803 .

Comiso J C . 1990 . Arctic multiyear ice classification and summer ice cover using passive microwave satellite data . Journal of Geophysical Research: Oceans , 95 ( C8 ): 13411 - 13422 , https://doi.org/10.1029/JC095iC08p13411 https://doi.org/10.1029/JC095iC08p13411 .

Comiso J C . 2012 . Large decadal decline of the arctic multiyear ice cover . Journal of Climate , 25 ( 4 ): 1176 - 1193 , https://doi.org/10.1175/JCLI-D-11-00113.1 https://doi.org/10.1175/JCLI-D-11-00113.1 .

Cui Y R , Zou B , Han Z et al . 2020 . Application of convolutional neural networks in satellite remote sensing sea ice image classification: a case study of sea ice in the Bohai Sea . Haiyang Xuebao , 42 ( 9 ): 100 - 109 , https://doi.org/10.3969/j.issn.0253-4193.2020.09.011. https://doi.org/10.3969/j.issn.0253-4193.2020.09.011. (in Chinese with English abstract)

Dabboor M , Geldsetzer T . 2014 . Towards sea ice classification using simulated RADARSAT Constellation Mission compact polarimetric SAR imagery . Remote Sensing of Environment , 140 : 189 - 195 , https://doi.org/10.1016/j.rse.2013.08.035 https://doi.org/10.1016/j.rse.2013.08.035 .

Dawson G , Landy J , Tsamados M et al . 2022 . A 10-year record of Arctic summer sea ice freeboard from CryoSat-2. Remote Sensing of Environment , 268 : 112744 , https://doi.org/10.1016/j.rse.2021.112744 https://doi.org/10.1016/j.rse.2021.112744 .

Fetterer F , Bertoia C , Ye J P . 1997 . Multi-year ice concentration from RADARSAT . In: Proceedings of IEEE International Geoscience and Remote Sensing Symposium Proceedings . Remote Sensing–A Scientific Vision for Sustainable Development. IEEE , Singapore, Singapore . p. 402 - 404 , https://doi.org/10.1109/IGARSS.1997.615897 https://doi.org/10.1109/IGARSS.1997.615897 .

Gao L , Li X F , Kong F Z et al . 2022 . AlgaeNet: a deep-learning framework to detect floating green algae from optical and SAR imagery . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 15 : 2782 - 2796 , https://doi.org/10.1109/JSTARS.2022.3162387 https://doi.org/10.1109/JSTARS.2022.3162387 .

Geldsetzer T , Yackel J , Tomar K S et al . 2023 . Melt pond detection on landfast sea ice using dual co-polarized Ku-band backscatter. Remote Sensing of Environment , 296 : 113725 , https://doi.org/10.1016/j.rse.2023.113725 https://doi.org/10.1016/j.rse.2023.113725 .

Gillioz A , Casas J , Mugellini E et al . 2020 . Overview of the transformer-based models for NLP tasks . In: Proceedings of 2020 Federated Conference on Computer Science and Information Systems . ACSIS, Sofia, Bulgaria . p. 179 - 183 , https://doi.org/10.15439/2020F20 https://doi.org/10.15439/2020F20 .

Hersbach H , Bell B , Berrisford P et al . 2020 . The ERA5 global reanalysis . Quarterly Journal of the Royal Meteorological Society , 146 ( 730 ): 1999 - 2049 , https://doi.org/10.1002/qj.3803 https://doi.org/10.1002/qj.3803 .

Holland M M , Bitz C M . 2003 . Polar amplification of climate change in coupled models . Climate Dynamics , 21 ( 3 ): 221 - 232 , https://doi.org/10.1007/s00382-003-0332-6 https://doi.org/10.1007/s00382-003-0332-6 .

Huang J X , Zhang T Y , Cao Y F et al . 2021 . The evolution of navigation performance of Northeast Passage under the scenario of Arctic sea ice melting . Acta Geographica Sinica , 76 ( 5 ): 1051 - 1064 , https://doi.org/10.11821/dlxb202105001. https://doi.org/10.11821/dlxb202105001. (in Chinese with English abstract)

Huang Y , Ren Y B , Li X F . 2024 . Deep learning techniques for enhanced sea-ice types classification in the Beaufort Sea via SAR imagery. Remote Sensing of Environment , 308 : 114204 , https://doi.org/10.1016/j.rse.2024.114204 https://doi.org/10.1016/j.rse.2024.114204 .

Huang Y , Ren Y B . 2023 . A U-Net sea ice classification model based on dual-polarized SAR images . Oceanologia et Limnologia Sinica , 54 ( 6 ): 1551 - 1563 , https://doi.org/10.11693/hyhz20230300063. https://doi.org/10.11693/hyhz20230300063. (in Chinese with English abstract)

Jiang M Z , Chen X W , Xu L L et al . 2024 . IceGCN: an interactive sea ice classification pipeline for SAR imagery based on graph convolutional network . Remote Sensing , 16 ( 13 ): 2301 , https://doi.org/10.3390/rs16132301 https://doi.org/10.3390/rs16132301 .

Karvonen J . 2017 . Baltic sea ice concentration estimation using SENTINEL-1 SAR and AMSR2 microwave radiometer data . IEEE Transactions on Geoscience and Remote Sensing , 55 ( 5 ): 2871 - 2883 , https://doi.org/10.1109/TGRS.2017.2655567 https://doi.org/10.1109/TGRS.2017.2655567 .

Kwok R . 2018 . Arctic sea ice thickness, volume, and multiyear ice coverage: losses and coupled variability (1958-2018) . Environmental Research Letters , 13 ( 10 ): 105005 , https://doi.org/10.1088/1748-9326/aae3ec https://doi.org/10.1088/1748-9326/aae3ec .

Li W , Hsu C Y , Tedesco M . 2024 . Advancing Arctic sea ice remote sensing with AI and deep learning: now and future . EGUsphere , 2024 : 1 - 36 , https://doi.org/10.3390/rs16203764 https://doi.org/10.3390/rs16203764 .

Li X F , Liu B , Zheng G et al . 2020 . Deep-learning-based information mining from ocean remote-sensing imagery . National Science Review , 7 ( 10 ): 1584 - 1605 , https://doi.org/10.1093/nsr/nwaa047 https://doi.org/10.1093/nsr/nwaa047 .

Li X F , Wang F . 2023 . Artificial Intelligence Oceanography . Springer, Singapore, Singapore , https://doi.org/10.1007/978-981-19-6375-9 https://doi.org/10.1007/978-981-19-6375-9 .

Liu H Y , Guo H D , Zhang L . 2015 . SVM-based sea ice classification using textural features and concentration from RADARSAT-2 Dual-Pol ScanSAR data . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 8 ( 4 ): 1601 - 1613 , https://doi.org/10.1109/JSTARS.2014.2365215 https://doi.org/10.1109/JSTARS.2014.2365215 .

Lohse J , Doulgeris A P , Dierking W . 2021 . Incident angle dependence of Sentinel-1 texture features for sea ice classification . Remote Sensing , 13 ( 4 ): 552 , https://doi.org/10.3390/rs13040552 https://doi.org/10.3390/rs13040552 .

Mori M , Kosaka Y , Watanabe M et al . 2019 . A reconciled estimate of the influence of Arctic sea-ice loss on recent Eurasian cooling . Nature Climate Change , 9 ( 2 ): 123 - 129 , https://doi.org/10.1038/s41558-018-0379-3 https://doi.org/10.1038/s41558-018-0379-3 .

Park J W , Korosov A A , Babiker M et al . 2020 . Classification of sea ice types in Sentinel-1 synthetic aperture radar images . The Cryosphere , 14 ( 8 ): 2629 - 2645 , https://doi.org/10.5194/tc-14-2629-2020 https://doi.org/10.5194/tc-14-2629-2020 .

Park J W , Won J S , Korosov A A et al . 2019 . Textural noise correction for Sentinel-1 TOPSAR cross-polarization channel images . IEEE Transactions on Geoscience and Remote Sensing , 57 ( 6 ): 4040 - 4049 , https://doi.org/10.1109/TGRS.2018.2889381 https://doi.org/10.1109/TGRS.2018.2889381 .

Qu Z F , Su J . 2023 . Improved algorithm for determining the freeze onset of Arctic sea ice using AMSR-E/2 data. Remote Sensing of Environment , 297 : 113748 , https://doi.org/10.1016/j.rse.2023.113748 https://doi.org/10.1016/j.rse.2023.113748 .

Radhakrishnan K , Scott K A , Clausi D A . 2021 . Sea ice concentration estimation: using passive microwave and SAR data with a U-Net and curriculum learning . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 14 : 5339 - 5351 , https://doi.org/10.1109/JSTARS.2021.3076109 https://doi.org/10.1109/JSTARS.2021.3076109 .

Rantanen M , Karpechko A Y , Lipponen A et al . 2022 . The Arctic has warmed nearly four times faster than the globe since 1979 . Communications Earth & Environment , 3 ( 1 ): 168 , https://doi.org/10.1038/s43247-022-00498-3 https://doi.org/10.1038/s43247-022-00498-3 .

Reichstein M , Camps-Valls G , Stevens B et al . 2019 . Deep learning and process understanding for data-driven Earth system science . Nature , 566 ( 7743 ): 195 - 204 , https://doi.org/10.1038/s41586-019-0912-1 https://doi.org/10.1038/s41586-019-0912-1 .

Ren Y B , Li X F , Yang X F et al . 2022 . Development of a dual-attention U-Net model for sea ice and open water classification on SAR images. IEEE Geoscience and Remote Sensing Letters , 19 : 4010205 , https://doi.org/10.1109/LGRS.2021.3058049 https://doi.org/10.1109/LGRS.2021.3058049 .

Sen R , Goswami S , Chakraborty B . 2019 . Jeffries-Matusita distance as a tool for feature selection . In: Proceedings of 2019 International Conference on Data Science and Engineering . IEEE, Patna, India . p. 15 - 20 , https://doi.org/10.1109/ICDSE47409.2019.8971800 https://doi.org/10.1109/ICDSE47409.2019.8971800 .

Serreze M C , Barry R G . 2011 . Processes and impacts of Arctic amplification: a research synthesis . Global and Planetary Change , 77 ( 1-2 ): 85 - 96 , https://doi.org/10.1016/j.gloplacha.2011.03.004 https://doi.org/10.1016/j.gloplacha.2011.03.004 .

Soh L K , Tsatsoulis C , Gineris D et al . 2004 . ARKTOS: an intelligent system for SAR sea ice image classification . IEEE Transactions on Geoscience and Remote Sensing , 42 ( 1 ): 229 - 248 , https://doi.org/10.1109/TGRS.2003.817819 https://doi.org/10.1109/TGRS.2003.817819 .

Soh L K , Tsatsoulis C . 1999 . Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices . IEEE Transactions on Geoscience and Remote Sensing , 37 ( 2 ): 780 - 795 , https://doi.org/10.1109/36.752194 https://doi.org/10.1109/36.752194 .

Stokholm A , Buus-Hinkler J , Wulf T et al . 2024 . The AutoICE challenge . The Cryosphere , 18 ( 8 ): 3471 - 3494 , https://doi.org/10.5194/tc-18-3471-2024 https://doi.org/10.5194/tc-18-3471-2024 .

Su H , Ji B W , Wang Y P . 2019 . Sea ice extent detection in the Bohai Sea using Sentinel-3 OLCI Data . Remote Sensing , 11 ( 20 ): 2436 , https://doi.org/10.3390/rs11202436 https://doi.org/10.3390/rs11202436 .

Su H , Wang Y P , Xiao J et al . 2013 . Improving MODIS sea ice detectability using gray level co-occurrence matrix texture analysis method: a case study in the Bohai Sea . ISPRS Journal of Photogrammetry and Remote Sensing , 85 : 13 - 20 , https://doi.org/10.1016/j.isprsjprs.2013.07.010 https://doi.org/10.1016/j.isprsjprs.2013.07.010 .

Walker N P , Partington K C , van Woert M L et al . 2006 . Arctic sea ice type and concentration mapping using passive and active microwave sensors . IEEE Transactions on Geoscience and Remote Sensing , 44 ( 12 ): 3574 - 3584 , https://doi.org/10.1109/TGRS.2006.881116 https://doi.org/10.1109/TGRS.2006.881116 .

Wang H Y , Li X F . 2024a . DeepBlue: advanced convolutional neural network applications for ocean remote sensing . IEEE Geoscience and Remote Sensing Magazine , 12 ( 1 ): 138 - 161 , https://doi.org/10.1109/MGRS.2023.3343623 https://doi.org/10.1109/MGRS.2023.3343623 .

Wang H Y , Li X F . 2024b . Expanding horizons: U-Net enhancements for semantic segmentation, forecasting, and super-resolution in ocean remote sensing. Journal of Remote Sensing , 4 : 0196 , https://doi.org/10.34133/remotesensing.0196 https://doi.org/10.34133/remotesensing.0196 .

Wang L , Scott K A , Xu L L et al . 2016 . Sea ice concentration estimation during melt from Dual-Pol SAR scenes using deep convolutional neural networks: a case study . IEEE Transactions on Geoscience and Remote Sensing , 54 ( 8 ): 4524 - 4533 , https://doi.org/10.1109/TGRS.2016.2543660 https://doi.org/10.1109/TGRS.2016.2543660 .

Wang Y H , Bi H B , Huang H J et al . 2019 . Satellite-observed trends in the Arctic sea ice concentration for the period 1979-2016 . Journal of Oceanology and Limnology , 37 ( 1 ): 18 - 37 , https://doi.org/10.1007/s00343-019-7284-0 https://doi.org/10.1007/s00343-019-7284-0 .

Xu H , Ren Y B . 2021 . Detecting sea ice of Bohai Sea using SAR images based on a hybrid loss U-Net model . Haiyang Xuebao , 43 ( 6 ): 157 - 170 , https://doi.org/10.12284/hyxb2021084. https://doi.org/10.12284/hyxb2021084. (in Chinese with English abstract)

Ye Y F , Heygster G , Shokr M . 2016 . Improving multiyear ice concentration estimates with reanalysis air temperatures . IEEE Transactions on Geoscience and Remote Sensing , 54 ( 5 ): 2602 - 2614 , https://doi.org/10.1109/TGRS.2015.2503884 https://doi.org/10.1109/TGRS.2015.2503884 .

Zakhvatkina N Y , Alexandrov V Y , Johannessen O M et al . 2013 . Classification of sea ice types in ENVISAT synthetic aperture radar images . IEEE Transactions on Geoscience and Remote Sensing , 51 ( 5 ): 2587 - 2600 , https://doi.org/10.1109/TGRS.2012.2212445 https://doi.org/10.1109/TGRS.2012.2212445 .

Zhang X , Dierking W , Zhang J et al . 2016 . Retrieval of the thickness of undeformed sea ice from simulated C-band compact polarimetric SAR images . The Cryosphere , 10 ( 4 ): 1529 - 1545 , https://doi.org/10.5194/tc-10-1529-2016 https://doi.org/10.5194/tc-10-1529-2016 .

Zhang X , Zhang J , Meng J M et al . 2013 . Analysis of multi-dimensional SAR for determining the thickness of thin sea ice in the Bohai Sea . Chinese Journal of Oceanology and Limnology , 31 ( 3 ): 681 - 698 , https://doi.org/10.1007/s00343-013-2057-7 https://doi.org/10.1007/s00343-013-2057-7 .

Zhang X , Zhu Y X , Zhang J et al . 2021 . Assessment of arctic sea ice classification ability of Chinese HY-2B dual-band radar altimeter during winter to early spring conditions . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 14 : 9855 - 9872 , https://doi.org/10.1109/JSTARS.2021.3114228 https://doi.org/10.1109/JSTARS.2021.3114228 .

Zhao L , Xie T , Perrie W et al . 2023 . Deep-learning-based sea ice classification with Sentinel-1 and AMSR-2 data . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 16 : 5514 - 5525 , https://doi.org/10.1109/JSTARS.2023.3285857 https://doi.org/10.1109/JSTARS.2023.3285857 .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

A physics-enhanced deep-learning model for estimating turbid shallow water depth from SAR images

Prediction of sea surface pCO₂ in the South China Sea using Spatiotemporal Convolutional LSTM model

Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images

A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean

Parameterization of turbulent mixing by deep learning in the continental shelf sea east of Hainan Island