Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier-Feature Assembly

doi:10.1109/LGRS.2017.2743339

	Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier-Feature Assembly
	Shen, Xiaoyi 1; Zhang, Jie 2; Zhang, Xi 2; Meng, Junmin 2; Ke, Changqing 1
	2017-11
关键词	Altimeter waveform classification Cryosat-2 (CS-2) machine learning sea ice type
卷号	14
期号	11
DOI	10.1109/LGRS.2017.2743339
页码	1948-1952
英文摘要	Sea ice type is one of the most sensitive variables in Arctic ice monitoring and detailed information about it is essential for ice situation evaluation, vessel navigation, and climate prediction. Many machine-learning methods including deep learning can be employed for ice-type detection, and most classifiers tend to prefer different feature combinations. In order to find the optimal classifier-feature assembly (OCF) for sea ice classification, it is necessary to assess their performance differences. The objective of this letter is to make a recommendation for the OCF for sea ice classification using Cryosat-2 (CS-2) data. Six classifiers including convolutional neural network (CNN), Bayesian, K nearest-neighbor (KNN), support vector machine (SVM), random forest (RF), and back propagation neural network (BPNN) were studied. CS-2 altimeter data of November 2015 and May 2016 in the whole Arctic were used. The overall accuracy was estimated using multivalidation to evaluate the performances of individual classifiers with different feature combinations. Overall, RF achieved a mean accuracy of 89.15%, followed by Bayesian, SVM, and BPNN (similar to 86%), outperforming the worst (CNN and KNN) by 7%. Trailingedge width (TeW) and leading-edge width (LeW) were the most important features, and feature combination of TeW, LeW, Sigma0, maximum of the returned power waveform (MAX), and pulse peakiness (PP) was the best choice. RF with feature combination of TeW, LeW, Sigma0, MAX, and PP was finally selected as the OCF for sea ice classification and the results that demonstrated this method achieved a mean accuracy of 91.45%, which outperformed the other state-of-art methods by 9%.
会议录	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
会议录出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
会议录出版地	445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA
语种	英语
资助项目	European Space Agency through Dragon-4 Programme[32292]
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000413955500014
WOS关键词	RADAR ALTIMETER
内容类型	会议论文
源URL	[http://ir.fio.com.cn:8080/handle/2SI8HI0U/26996]
专题	自然资源部第一海洋研究所
通讯作者	Zhang, Xi
作者单位	1.Nanjing Univ, Collaborat Innovat Ctr South China Sea Studies, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing 210023, Jiangsu, Peoples R China 2.State Ocean Adm, Inst Oceanog 1, Qingdao 266061, Peoples R China
推荐引用方式 GB/T 7714	Shen, Xiaoyi,Zhang, Jie,Zhang, Xi,et al. Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier-Feature Assembly[C]. 见:.