Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data

doi:10.3390/rs13081452

	Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data
	Zhang, Tianyu 2,3,4,5; Yang, Ying 2,3,4,5; Shokr, Mohammed 6; Mi, Chunlei 1,7; Li, Xiao-Ming 8,9; Cheng, Xiao 3,4,5; Hui, Fengming 3,4,5
刊名	REMOTE SENSING
	2021-04-01
卷号	13 期号:8 页码:22
关键词	Gaofen-3 polarimetric data sea ice classification residual convolutional network
DOI	10.3390/rs13081452
通讯作者	Hui, Fengming(huifm@mail.sysu.edu.cn)
英文摘要	In this paper, the performance of C-band synthetic aperture radar (SAR) Gaofen-3 (GF-3) quad-polarization Stripmap (QPS) data is assessed for classifying late spring and summer sea ice types. The investigation is based on 18 scenes of GF-3 QPS data acquired in the Arctic Ocean in 2017. In this study, floe ice (FI), brash ice (BI) between floes and open water (OW, ice-free area) were classified based on a mini sea ice residual convolutional network, which we call MSI-ResNet. While investigating the optimal patch size for MSI-ResNet, we found that, as the patch size continues to grow, the classification accuracy first increases and then decreases. A patch size of 31 x 31 was found to achieve the best performance. The performance of classification using different polarization combinations from the QPS data was also assessed. The vertical-vertical (VV) polarization input overestimates the FI category while incorrectly identifying most of the BI as FI. The VH polarization produces a synchronous improvement in FI, BI, and OW discrimination, with a higher overall accuracy and kappa coefficient (91.09% and 0.85, respectively) than the VV polarization (83.37% and 0.70, respectively). The combination of VV and vertical-horizontal (VH) polarizations presents a modest precision improvement for BI and OW together with a slight overestimation for FI. With VV, VH, and horizontal-horizontal (HH) polarization data as the inputs, the user's accuracy improves to 95.12%, 93.42%, and 95.17% for FI, BI, and OW, respectively. The accuracy was assessed against visual interpretation of the sea ice classes in the images using a stratified sampling method. The application of the MSI-ResNet method to data covering the Beaufort Sea and the north of the Severnaya Zemlya archipelago was found to achieve a high overall accuracy (kappa) of 94.62% (+/- 0.92) and 94.23% (+/- 0.90), respectively. This is similar to the classification accuracy obtained in the Fram Strait. From the results of this study, it is shown that the MSI-ResNet method performs better than the classical support vector machine (SVM) classifier for sea ice discrimination. The GF-3 QPS mode data also show more details in discriminating scattered sea ice floes than the coincident Sentinel-1A Extra Wide (EW) swath mode data.
资助项目	National Natural Science Foundation of China[41976214] ; National Key Research and Development Project of China[2018YFC1407100]
WOS关键词	SYNTHETIC-APERTURE RADAR ; X-BAND SAR ; NEURAL-NETWORKS ; ACCURACY ; SEGMENTATION ; PARAMETERS ; TEXTURE ; IMAGERY
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	MDPI
WOS记录号	WOS:000644690500001
资助机构	National Natural Science Foundation of China ; National Key Research and Development Project of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/161678]
专题	中国科学院地理科学与资源研究所
通讯作者	Hui, Fengming
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Beijing Normal Univ, State Key Lab Remote Sensing Sci, Coll Global Change & Earth Syst Sci, Beijing 100875, Peoples R China 3.Sun Yat Sen Univ, Sch Geospatial Engn & Sci, Zhuhai 519000, Peoples R China 4.Southern Marine Sci & Engn Guangdong Lab Zhuhai, Zhuhai 519000, Peoples R China 5.Univ Corp Polar Res, Beijing 100875, Peoples R China 6.Environm & Climate Change Canada, Sci & Technol Branch, Toronto, ON M3H 5T4, Canada 7.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 8.Chinese Acad Sci, Key Lab Digital Earth Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China 9.Hainan Key Lab Earth Observat, Sanya 572029, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Tianyu,Yang, Ying,Shokr, Mohammed,et al. Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data[J]. REMOTE SENSING,2021,13(8):22.
APA	Zhang, Tianyu.,Yang, Ying.,Shokr, Mohammed.,Mi, Chunlei.,Li, Xiao-Ming.,...&Hui, Fengming.(2021).Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data.REMOTE SENSING,13(8),22.
MLA	Zhang, Tianyu,et al."Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data".REMOTE SENSING 13.8(2021):22.