A unified C-band and Ku-band GMF determined by using neural network approach

ZOU Ju-hong; LIN Ming-sen; PAN De-lu; CHEN Zheng-hua; YANG Le

Article Contents

Article Navigation > Haiyang Xuebao > 2008 > 30(5): 23-28

ZOU Ju-hong, LIN Ming-sen, PAN De-lu, CHEN Zheng-hua, YANG Le. A unified C-band and Ku-band GMF determined by using neural network approach[J]. Haiyang Xuebao, 2008, 30(5): 23-28.

Citation:

ZOU Ju-hong, LIN Ming-sen, PAN De-lu, CHEN Zheng-hua, YANG Le. A unified C-band and Ku-band GMF determined by using neural network approach[J]. Haiyang Xuebao, 2008, 30(5): 23-28.

ZOU Ju-hong, LIN Ming-sen, PAN De-lu, CHEN Zheng-hua, YANG Le. A unified C-band and Ku-band GMF determined by using neural network approach[J]. Haiyang Xuebao, 2008, 30(5): 23-28.

Citation:

ZOU Ju-hong, LIN Ming-sen, PAN De-lu, CHEN Zheng-hua, YANG Le. A unified C-band and Ku-band GMF determined by using neural network approach[J]. Haiyang Xuebao, 2008, 30(5): 23-28.

PDF( 1904 KB)

A unified C-band and Ku-band GMF determined by using neural network approach

1.
State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012 China;Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China
2.
National Satellite Ocean Application Center, National Marine Environmental Forecasting Center, State Oceanic Administration, Beijing 100081, China
3.
State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012 China

Received Date: 2008-05-28
Rev Recd Date: 2008-06-28

Abstract

Abstract

The geophysical model function(GMF)describes the relationship between backscatteringand sea surface wind,so that wind vectors can be retrieved from backscattering measurement. The GMF plays animportantrole in ocean wind vectorretrievals,its performance will directly influence the accuracy of the retrieved wind vector. Neural network(NN)approach is used to develop a unified GMF for C-band and Ku-band(NN-GMF).Empirical GMF CMOD4 and QSCAT-1 are used to generate the simulated training data-set,and Gaussian noise ata signal noise ratio of 30 dB is added to the data-set to simulate the noise in the backscattering measurement. The NN-GMF employs radio frequency as an additional parameter,so it can be applied for both C-band and Ku-band. A nalysis shows that the normalized backscattering coefficient predicted by the NN-GMF is comparable with the normalized backscattering coefficient predicted by CMOD4 and QSCAT-1. Also the wind vectors retrieved from the NN-GMF and empirical GMF CMOD4 and Qscat-1 are comparable,indicating that the NN-GMF is as effective as the empirical GMF,and has the advantages of the universal form.
- GMF,
- neural network,
- CMOD4,
- QSCAT-1

FullText(HTML)

References(17)

References

CHI Chong-yun,LI Fuk K.A comparative study of several wind estimation algorithms for spaceborne scatterometer[J].IEEE Transactions on Geoscience and Remote Sensing,1988,26(2):115-121.

HOWARD Schultz.A circular median filter approach for resolving directional ambiguities in wind fields retrieved from spaceborne scatterometer data[J].J Geophys Res,1990,95(C4):5291-5303.

LECOMPTE P.CMOD4 model description[K],issue 1.2.Frascati,Italy:ESA/ESRIN,1993:1-8.

JPL.QuikSCAT Science Data Product User's Manual[K].Vet 2.1.California:JPL NASA.2001:36-42.

SCHROEDER L C,BOGGS D H,DOME G J,et al.The relationship between wind vector and normalized radar cross section used to derive SEASAT-A satellite scatterometer winds[J].J Geophys Res,1982,87 (5):3318-3336.

NGH1EM S V,LI F K,NEUMANN G.Ku-band ocean backscatter functions for surface wind retrieval[C]//Proceedings of the 1996 International Geoscience and Remote Sensing Symposium on Remote Sensing for a Sustainable Future.Lincoln,NE.New York:WileyIEEE Press,1996:1469-1471.

WENTZ F J,PETEHERYCH S,THOMAS L A.A model function for ocean radar cross sections aT-14.6 GHz[J].J Geophys Res,1984,89(C3):3689-3704.

WENTZ F J,FREILICH M H,SMITH D K.NSCAT-2 geophysical model function[C]//1998 Fall AGU Meet.San Francisco,CA.Washington D.C.:AGU Press,1998.

WENTZ F J,SMITH D K.A model function for the ocean-normalized radar cross section aT-14 GHz derived from NSCAT observations[J].J GeophysRes,1999,104(C5):11499-11514.

Hans Hersbach Research Department.CMOD5:an improved geophysical model function for ERS C-band scatterometry[G]//ECMWF Technical Memoranda No.395.Berkshize RG29AX,England:ECMWF,2003.

RICHAUME P,BADRAN F,CREPON M,et al.Neural network wind retrieval from ERS—1 scatterometer data[J].J Geophys Res,2000,105(C4):8737-8751.

THIRIA S,MEJIA C,BADRAN F.A neural network approach for modelling nonlinear transfer functions:application for wind retrieval from spaceborne scatterometer data[J].J Geophys Res,1993,98(C12):22827-22841.

MEJ IA C,THIRIA S,BADRAN F,et al.Determination of the geophysical model function of ERS1 scatterometer by the use of neural networks[J].J Geophys Res,1998,103 (C6):12853-12868.

MEJ I A C,BADRAN F,BENTAMY A,et al.Determination of the geophysical model function of NSCAT and its corresponding variance by the use of neural networks[J].J Geophys Res,1999,104:11539 11556.

LIN Ming-sen,SONG Xin gai,JIANG Xin gwei.Neural network wind retrieval from ERS-1/2 seatterometer data[J].Aeta Oceano logica Sinica,2006,25(3):35-39.

工新中,姜景山.旋转扫描散射计海面风场检测仿真研究[J].遥感学报,1 997,1(3):185-191.

WENTZ F J.Measurement of oceanic wind vector using satellite microwave radiometers[J].IEEE Transactions on Geoseienee and Remote Sensing,1992,30 (5):960-972.

Relative Articles

Supplements(0)

Cited By

Proportional views