Inversion study of the rough sea surface wind speed and sea surface salinity based on the support vector machine

ZHANG Qinghe; LIANG Weibo

doi:10.13443/j.cjors.2015102601

Volume 31 Issue 5

Oct. 2016

Turn off MathJax

Article Contents

Abstract

References

CHINESE JOURNAL OF RADIO SCIENCE > 2016 > 31(5): 896-905. > DOI: 10.13443/j.cjors.2015102601

ZHANG Qinghe, LIANG Weibo. Inversion study of the rough sea surface wind speed and sea surface salinity based on the support vector machine[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2016, 31(5): 896-905. doi: 10.13443/j.cjors.2015102601

Reference format:

PDF (1147 KB)

Inversion study of the rough sea surface wind speed and sea surface salinity based on the support vector machine

ZHANG Qinghe^,,
LIANG Weibo

College of Science, Three Gorges University, Yichang 443002, China

More Information

Received Date: October 25, 2015
Available Online: December 30, 2020
Published Date: October 29, 2016

Graphical Abstract

Abstract

Abstract

In this paper, the support vector machine(SVM) regression techniques are applied to the inversion of sea state parameters (e.g. salinity and wind speed of the sea surface). The two scale model (TSM) is used to simulate backscattering coefficients of the rough sea surface with different radar parameters. After the sensitivity analysis, the L band (1.4 GHz) and the C band (6.8 GHz) are selected with appropriate angles as radar parameters. Then a variety of schemes of inversion are designed, in which single-frequency dual-polarization double angle, dual-frequency dual-polarization double angle and the ratio between the VV and HH polarization backscattering coefficients are chosen respectively as the samples information. After appropriate training, the SVM forecasting model is applied to inverse the salinity and wind speed of the sea surface. As shown by the results, at the C band, the inversion of the sea surface wind speed bears the highest accuracy, whereas at the L band, the inversion of the sea surface salinity demonstrates the highest accuracy when the ratio between backscattering coefficients is chosen as the samples information. The anti-noise performance of the SVM model is also examined, and the results show that the SVM model performs favorably in the sea state parameter inversion problem.
- support vector machine (SVM),
- two scale model(TSM),
- inversion,
- sea surface wind speed,
- sea surface salinity

FullText(HTML)

References (27)

References

[1]	ATLAS R, HOFFMAN R N, LEIDNER S M, et al. The effects of marine winds from scatterometer data on weather analysis and forecasting[J]. Bulletin of the American meteorological society, 2001, 82(9): 1965-1990. doi: 10.1175/1520-0477(2001)082<1965:TEOMWF>2.3.CO;2
[2]	LAGERLOEF G, COLOMB F R, LEVINE D M, et al. The Aquarius/SAC-D mission: designed to meet the salinity remote sensing challenge[J]. Oceanography, 2008, 21(1): 68-81. doi: 10.5670/oceanog
[3]	OSAMU I, MASANOBU S. An L-band ocean geophysical model function derived from PALSAR[J]. IEEE transactions on geoscience and remote sensing, 2009, 47(7): 1925-1936. doi: 10.1109/TGRS.2008.2010864
[4]	SIMON H Y, STEVE J D, ALEXANDER G F, et al. Passive and Active L-band microwave observations and modeling of ocean surface winds[J]. IEEE transactions on geoscience and remote sensing, 2010, 48(8): 3087-3100. doi: 10.1109/TGRS.2010.2045002
[5]	SIMON H Y, JULIAN C. Sea surface and wind retrieval using combined passive and active L-band microwave observations[J]. IEEE transactions on geoscience and remote sensing, 2012, 50(4): 1022-1032. doi: 10.1109/TGRS.2011.2165075
[6]	RIVAS M B, STOFFELEN A, ZADELHOFF G J, et al. The benefit of HH and VV polarizations in retrieving extreme wind speeds for an ASCAT type scatterometer[J]. IEEE transactions on geoscience and remote sensing, 2014, 52(7): 4273-4280. doi: 10.1109/TGRS.2013.2280876
[7]	ZOU J H, XIE X T, ZHANG Y, et al. Wind retrieval processing for HY-2A microwave scatterometer[C]//Proceedings of the IEEE Geoscience and Remote Sensing Symposium. Greece, 2014: 5160-5163.
[8]	TANG W Q, YUEH S, FORE A, et al. Aquarius combined active passive algorithm for ocean surface salinity and wind retrieval[C]//Proceedings of the General Assembly and Scientific Symposium. Greece, 2014: 1-4.
[9]	SAID F, JOHNSEN H, CHAPRON B, et al. An ocean wind Doppler model based on the generalized curvature ocean surface scattering model[J]. IEEE transactions on geoscience and remote sensing, 2015, 53(12): 6632-6638. doi: 10.1109/TGRS.2015.2445057
[10]	CLARIZIA M P, RUF C S, JALES P, et al. Spaceborne GNSS-R minimum variance wind speed estimator[J]. IEEE transactions on geoscience and remote sensing, 2014, 52(11): 6829-6843. doi: 10.1109/TGRS.2014.2303831
[11]	周旋, 叶小敏, 于暘, 等.基于GNSS-R的海面风速探测技术研究[J].电子与信息学报, 2013, 35(7): 1575-1580. http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201307008 ZHOU X, YE X M, YU Y, et al. Sea surface wind speed measurement using GNSS reflection signal[J]. Journal of electronics & information technology, 2013, 35(7): 1575-1580. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201307008
[12]	CHEN K S, TZENG Y C, CHEN P C. Retrieval of ocean winds from satellite scatterometer by a neural network[J]. IEEE transactions on geoscience and remote sensing, 1999, 37(2): 247-256. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=739159
[13]	林明森, 宋新改, 彭海龙, 等.散射计资料的风场神经网络反演算法研究[J].国土资源遥感, 2006, 68(2): 8-11. doi: 10.3969/j.issn.1001-070X.2006.02.003 LIN M S, SONG X G, PENG H L, et al. Neural network wind retrieval from scatterometer data[J]. Remote sensing for land & resources, 2006, 68(2): 8-11. (in Chinese) doi: 10.3969/j.issn.1001-070X.2006.02.003
[14]	解学通, 郁文贤, 郭丽青, 等.基于遗传算法的微波散射计海面风矢量反演研究[J].海洋通报, 2008, 27(4): 1-11. doi: 10.3969/j.issn.1001-6392.2008.04.001 XIE X T, YU W X, GUO L Q, et al. Research on Genetic algorithm based on ocean wind vector retrieval for microwave scatterometer[J]. Marine science bulletin, 2008, 27(4): 1-11. (in Chinese) doi: 10.3969/j.issn.1001-6392.2008.04.001
[15]	王署曜, 楚晓亮, 徐坤, 等. OS081H高频地波雷达系统海面风向反演实验研究[J].电子与信息学报, 2014, 36(6): 1400-1405. http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201406020 WANG S Y, CHU X L, XU K, et al. Experimental research on inversion of wind direction with HFSWR OS081H[J]. Journal of electronics & information technology, 2014, 36(6): 1400-1405. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dzkxxk201406020
[16]	GABARRO C, FONT J, CAMPS A, et al. Sea surface salinity and wind speed retrieval from a tower-based L-band radiometer in the NW mediterranean[C]//Proceedings of the IEEE on Remote Sensing. Spain, 2002: 761-769.
[17]	AMMAR A, LABROUE S, OBLIGIS E, et al. Sea surface salinity retrieval for the SMOS mission using neural networks[J]. IEEE transactions on geoscience and remote sensing, 2008, 46(3): 754-764. doi: 10.1109/TGRS.2008.915547
[18]	卢红丽, 王振占, 殷晓斌.利用SMOS卫星数据反演海洋盐度方法研究[J].遥感技术与应用, 2014, 29(3): 401-409. http://d.old.wanfangdata.com.cn/Periodical/ygjsyyy201403005 LU H L, WANG Z Z, YIN X B. Research of the sea surface salinity retrieval method based on SMOS data[J]. Remote sensing technology and application, 2014, 29(3): 401-409. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/ygjsyyy201403005
[19]	严明, 严卫, 王迎强, 等.基于微波遥感的海表面盐度探测机制研究进展[J].遥感信息, 2015, 30(2): 17-25. doi: 10.3969/j.issn.1000-3177.2015.02.003 YAN M, YAN W, WANG Y Q, et al. Progress in sea surface salinity probe technology based on microwave remote sensing[J]. Remote sensing information, 2015, 30(2): 17-25. (in Chinese) doi: 10.3969/j.issn.1000-3177.2015.02.003
[20]	VAPNIK V. Statistical learning theory[M]. New York: Wiley, 1998.
[21]	TONG Y B, YANG D K, ZHANG Q H. Wavelet kernel support vector machines for sparse approximation[J]. Journal of electronics (China), 2006, 23(4): 539-542. doi: 10.1007/s11767-004-0202-3
[22]	ZHANG L, LIN F, ZHANG B. Support vector machine learning for image retrieval[C]//Proceedings of the IEEE on Image Processing. Greece, 2001: 107-118.
[23]	LEOPOLD E, KINDERMANN J. Text categorization with support vector machines. How to represent texts in input space?[J]. Machine learning, 2002, 46: 423-444. doi: 10.1023/A:1012491419635
[24]	IPLIKCI S. Support vector machines-based generalized predictive control[J]. International journal of robust and nonlinear control, 2006, 16(5): 813-862. http://d.old.wanfangdata.com.cn/Periodical/zdhxb200711010
[25]	许小剑, 李晓飞, 刁桂杰, 等.时变海面雷达目标散射现象学模型[M].北京:国防工业出版社, 2013: 10-53.
[26]	郭立新, 王蕊, 吴振森.随机粗糙面散射的基本理论与方法[M].北京:科学出版社, 2009: 56-61.
[27]	MEISSNER T, WENTZ F J. The complex dielectric constant of pure and sea water from microwave satellite observations[J]. IEEE transactions on geoscience and remote sensing, 2004, 42(9): 1836-1849. doi: 10.1109/TGRS.2004.831888

[1]	LI Xiaohan, YAN Qiushuang, FAN Chenqing, ZHANG Jie. Deep learning-based sea surface wind speed retrieval method for Sentinel-1 dual-polarimetric SAR under typhoon sea state[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2024, 39(6): 1095-1101. DOI: 10.12265/j.cjors.2023280
[2]	LI Zichong, JIANG Gengming. Intercalibration of FY-3D MWRI and sea surface temperature retrieval[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2024, 39(2): 214-224. DOI: 10.12265/j.cjors.2023077
[3]	GUO Xiangming, ZHANG Yusheng, ZHANG Hui, KANG Shifeng. Modeling through sea surface and its application in the evaporation duct propagation[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2022, 37(2): 183-188. DOI: 10.12265/j.cjors.2021215
[4]	CHENG Yinhe, XU Jianhui, ZHANG Yusheng, GUO Xiangming, YOU Zhiwei. Influence of sea surface temperature on numerical simulation of lower atmospheric duct over the South China Sea[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2022, 37(1): 40-47. DOI: 10.12265/j.cjors.2021004
[5]	QI Yongqiang, ZHANG Bo, YANG Dongkai, ZHANG Yanzhong. Simulation on airborne GNSS echo signal from sea surface[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2017, 32(3): 286-291. DOI: 10.13443/j.cjors.2017021601
[6]	ZOU Gaoxiang, TONG Chuangming, SUN Hualong, WANG Tong WANG Tong, PENG Peng. Brewster effect from composite rough surface of ground and sea in adjacent region[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2016, 31(6): 1036-1045. DOI: 10.13443/j.cjors.2016112001
[7]	MENG Xiao, GUO Lixin, HUANG Qingqing, LI Juan. EM scattering from the sea surface based on the parallelized two scale model ray tracing[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2016, 31(4): 725-730. DOI: 10.13443/j.cjors.2015072502
[8]	WEI Yinyu, WU Zhensen, LU Yue. Electromagnetic scattering simulation of Kelvin wake in rough sea surface[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2016, 31(3): 438-442. DOI: 10.13443/j.cjors.2015071002
[9]	ZHANG Lan, WU Xiongbin, CHEN Xiaofeng, LI Yan. Sea surface conductivity inversion with HF surface wave radar[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2014, 29(4): 706-710+722. DOI: 10.13443/j.cjors.2013080501
[10]	WANG Xiaobing, WU Zhensen, ZHANG Yuan, YUE Hui, LIANG Zichang. Electromagnetic backwardscattering measurements of rough sea surface in near field[J]. CHINESE JOURNAL OF RADIO SCIENCE, 2013, 28(1): 28-32.

Cited By

Cited by

Periodical cited type(0)

Other cited types(5)

Get Citation

PDF

XML

Article views (221) PDF downloads (198) Cited by(5)

Latest Notice

Inversion study of the rough sea surface wind speed and sea surface salinity based on the support vector machine

Abstract

References

Related Articles

Cited by

Periodical cited type(0)

Other cited types(5)

Catalog

Related

Latest Notice

Inversion study of the rough sea surface wind speed and sea surface salinity based on the support vector machine

Abstract

References

Related Articles

Cited by

Periodical cited type(0)

Other cited types(5)

Catalog

Related

Export File

Citation

Format

Content