Simulating radiative transfer forward model using support vector machine technique

doi:10.11834/jrs.20090246

Views : 0 下载量: 547 CSCD: 0

PDF
Export
Share
Collection
Album

Simulating radiative transfer forward model using support vector machine technique
Vol. 13, Issue 2, Pages: 257-262(2009)
Published：2009
DOI： 10.11834/jrs.20090246
稿件说明：

移动端阅览

[1]谭永强,费建芳.应用SVM技术模拟前向辐射传输模式[J].遥感学报,2009,13(02):257-262. DOI： 10.11834/jrs.20090246.

Simulating radiative transfer forward model using support vector machine technique[J]. Journal of Remote Sensing, 2009, 13(2): 257-262. DOI： 10.11834/jrs.20090246.

摘要

提出了一种利用支持向量机（SVM）模拟前向辐射传输模式的方法。利用欧洲中期天气预报中心（ECMWF）的RTTOV

前向辐射传输模式和60L-SD廓线集生成了AMSU-A模拟亮温资料

用模拟亮温和相应的廓线集资料组成训练样本和检验样本

采用SVM方法进行训练。对检验样本的模拟显示

SVM可以用于描写前向辐射传输模式中的非线性映射关系

较好地由大气廓线集资料模拟出与其相关的AMSU-A仪器5—14通道亮温

其中通道6—14的均方根误差在0.1K以内

平均误差算术平均值在0.01K以内。通过多元线性回归方法对温度廓线进行反演试验

发现用SVM模拟的亮温可以用于温度廓线反演

其反演精度可以达到甚至高于RTTOV

计算的亮温。

Abstract

Based on Support Vector Machine（SVM）

a technique simulating radiative transfer forward model is presented. Using European Centre for Medium-Range Weather Forecasts （ECMWF） RTTOV

radiative transfer forward model and 60L

D profile database

we simulate the brightness temperature received in AMSU-A instrument. Combine this brightness temperature datasets and correspondence profile datasets as training and validation database. After training the SVM network

the simulating technique is validated. The results show that SVM network describes the nonlinear projection relationship between input space and output space very well

and the simulated brightness temperature of channel 5—14 is precise. The RMS error of channel 6—14 is less than 0.1K and the mean standard deviation is less than 0.01K. In order to find whether SVM simulated brightness temperature is appropriate for temperature retrieval

muti-regression retrieval method is used to retrieve temperature profile. Experiment result shows that the SVM simulate brightness temperature is appropriate for the purpose

and the retrieval precision is not only equally but also a little more precise than the RTTOV

simulated brightness temperature.