光电工程, 2010, 37 (8): 127, 网络出版: 2010-09-07
基于GA 优选参数的SVR水质参数遥感反演方法
A Method for Water Quality Remote Retrieval Based on Support Vector Regression with Parameters Optimized by Genetic Algorithm
高分辨遥感影像 遗传算法 支持向量回归 水质反演 high-resolution remote sensing image genetic algorithms support vector regression water quality retrievals
摘要
为进一步提高多光谱图像水质反演的精度,提出了一种基于GA 优选参数的SVR 水质参数遥感反演模型。该模型利用高分辨率多光谱遥感SPOT-5 数据和水质实地监测数据,采用CV 估计模型推广误差并使用GA 优选SVR 模型参数,实现了模型参数的自动全局优选,在训练好的SVR 模型基础之上对水质进行反演。以渭河陕西段为例进行实证研究,实验结果表明,本文提出的水质反演模型较常规的线性回归模有更高的反演精度,为内陆河流环境遥感监测提供了一种新方法。
Abstract
In order to improve water quality retrievals of multi-spectral image accurately, a model for water quality remote retrieval is put forward based on Support Vector Regression (SVR) with parameters optimized by genetic algorithm. The model based on high-resolution multi-spectral remote SPOT-5 data and the water quality field data, uses CV to estimate the promote error. And parameters of SVR model are optimized by Genetic Algorithm. The global optimization of model parameters is achieved. Then, water quality is retrieved by the trained SVR. The proposed model is applied to the water quality retrievals of Weihe River in Shaanxi Province. The result of experiment shows that the developed model has more accuracy than that of the routine linear regression model,which provides a new approach for remote sensing monitoring of environment in inland rivers.
何同弟, 李见为, 黄鸿. 基于GA 优选参数的SVR水质参数遥感反演方法[J]. 光电工程, 2010, 37(8): 127. HE Tong-di, LI Jian-wei, HUANG Hong. A Method for Water Quality Remote Retrieval Based on Support Vector Regression with Parameters Optimized by Genetic Algorithm[J]. Opto-Electronic Engineering, 2010, 37(8): 127.