X-波段雷达近海海浪频谱反演的神经网络模型

王静; 唐军武; 何宜军; 王鑫; 潘玉方

doi:10.3969/j.issn.0253 4193.2013.02.006

X-波段雷达近海海浪频谱反演的神经网络模型

doi: 10.3969/j.issn.0253 4193.2013.02.006

1.
遥感科学国家重点实验室, 北京 100101;中国科学院遥感应用研究所, 北京 100101
2.
遥感科学国家重点实验室, 北京 100101;国家海洋局国家海洋技术中心, 天津 300112
3.
中国科学院海洋研究所, 山东青岛 266071
4.
国家海洋局国家海洋技术中心, 天津 300112
5.
国家海洋局第二海洋研究所, 浙江杭州 310012

基金项目: 海洋公益性行业科研专项(201005035);海洋可再生能源专项资金项目(GHME2011ZC04;GHME2012ZC02)。

计量
- 文章访问数: 1918
- HTML全文浏览量: 16
- PDF下载量: 1457
- 被引次数: 0
出版历程
- 收稿日期: 2012-04-11
- 修回日期: 2012-10-01

The retrieval of a nearshore wave frequency spectrum with X-band radar based on neural network

1.
State Key Laboratory of Remote Sensing Science, Beijing 100101, China;Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China
2.
State Key Laboratory of Remote Sensing Science, Beijing 100101, China;National Ocean Technology Center, State Oecanic Administration, Tianjin 300112, China
3.
Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China
4.
National Ocean Technology Center, State Oecanic Administration, Tianjin 300112, China
5.
Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China

摘要

摘要: X-波段雷达作为国内海浪观测的一种新工具,在海浪频谱获取和有效波高反演方面仍存在较多问题。本文利用非线性回归方法,将现场实测浮标数据频谱和雷达一维图像谱分别与标准频谱模型进行拟合,发现浮标频谱和一维图像谱具有标准频谱的特征,能够较准确地获取相应的谱参数。提出了建立由雷达一维图像谱参数反演海浪频谱参数的神经网络模型,同时在模型中加入影像序列信噪比,进而反演有效波高,并将反演结果与现场实测数据和传统算法(建立影像序列信噪比与有效波高之间的线性回归方程)进行了对比,结果表明,获取谱参数的误差和反演有效波高的平均误差在20%以内,而传统算法计算有效波高平均误差在20%以上。
- X-波段雷达 /
- 海浪频谱 /
- 有效波高 /
- 非线性拟合 /
- 神经网络
Abstract: As a new tool for ocean wave measurement interiorly, X-band radar can be used to provide sea state information and a wave field can be get form an image sequence.However, there are still some problems in the retrieval of wave frequency spectrum and significant wave height (H_s).A nonlinear regression method was used to fit the in situ wave frequency spectrum and radar one-dimension image spectrum with standard PM, JONSWAP and TMA spectrum, and the basic form and the corresponding spectral parameters can be obtained accurately.Then, a generalized regression neural network model (GRNN) was introduced to retrieve the wave frequency spectral parameters from the one-dimensional radar image spectrum parameters.In the model, the signal-to-noise ratio (SNR) of the image sequence was added to set up a nonlinear relationship with H_s,and the inversion results with the in situ data and the traditional algorithm result (the establishment of the linear regression equation between SNR and H_s) were compared.The results show that the mean error of spectral parameters and significant wave height are less than 20%, while the mean error of the traditional algorithm is more than 20%.
- X-band radar /
- wave frequency spectrum /
- significant wave height /
- nonlinear regression /
- neural network

HTML全文

参考文献(15)

Young I R,Rosenthal W,Ziemer F.A three dimensional analysis of marine radar images for the determination of ocean wave directionality and surface currents[J].J Geophys Res,1985,90(C1): 1049-1059.

吴立中.二维小波转换应用于波场影像分析之研究.台湾: 国立成功大学, 2002.

吴立中.时空合域连续小波转换应用于非均匀波场分析之研究.台湾: 国立成功大学, 2008.

Nieto Borge J C,Rodríguez G,Hessner K,et al.Inversion of marine radar images for surface wave analysis[J].J Atmos Oc Tech, 2004, 21(8): 1291-1300.

Alpers W,Hasselmann K.Spectral signal to clutter and thermal noise properties of ocean wave imaging synthetic aperture radars[J].Int J Remote Sens,1982,3(4): 423-446.

Tucker M J.Waves in Ocean Engineering: Measurement,Analysis and Interpretation[M].London: Ellis Horwood, 1991.

Hasselmann K,Co-Authors.Measurement of wind-wave growth and swell decay during the joint North Sea wave (Project JONSWAP).Hamburg: Deutsch Hydrographisches Institut, 1973.

Kitagorodskii S A,Rasitskii V P, Zaslavskii M M.On phillip's theory of equilibrium rang in the spectra of wind-generated gravity waves[J].J Geophys Res,1975, 5: 410-420.

Bouws E,Günther H,Rosenthal W,et al.Similarity of the wind wave spectrum in finite depth water:1.Spectral form[J].J Geophys Res,1985, 90(C1): 975-986.

文圣常, 张大错, 郭佩芳, 等.改进的理论风浪频谱[J].海洋学报, 1990, 12(3): 271-283.

史峰, 王小川, 郁磊, 等.MATLAB神经网络30个案例分析[M].北京:北京航空航天大学出版社, 2010: 73-80.

尹彰, 周宗仁, 翁文凯, 等.有关利用船用雷达测波的再探讨//第三十届海洋工程研讨会论文集.台湾,2008: 187-192.

Maa J P Y,Ha H K.X Band Radar Wave Observation System.Virginia: Virginia Institute of Marine Science, 2005.

Wu L C,Doong D J,Kao C C, et al.Wave and current field extracted from marine radar images//The 15^th International Symposium on Ocean Wave Measurement and Analysis (WAVES2005).Spain,2005: 1-10.

吴克俭, 宋金宝, 楼顺里.论风浪的局域结构:Ⅰ.风浪的局域结构与局域小波能谱[J].海洋与湖沼, 1998, 29(4): 403-408.

施引文献

资源附件(0)

访问统计