摘要
综合分析了玉米叶面积指数与几种常见光谱植被指数相关性,确定主成分分析方法在反演叶面积指数中的作用。首先,借助MATLAB编程软件,以植被指数与玉米叶面积指数相关性最高为原则,选出遥感影像上各种植被指数,其波段组合为NDVI(752.4/701.5),RVI(752.4/701.5),MSR(752.4/701.5),SAVI(823.7/701.5),MSAVI(823.7/701.5),然后,对这5种植被指数进行主成分分析,建立LAI-VI多元逐步回归模型,并对模型精度进行验证,总体估测精度为96.237%。经实验验证,利用主成分分析方法在反演植被叶面积指数时能够起到较好的效果,具有广泛的应用前景。
This article gave a comprehensive analysis of correlation between leaf area index （LAI） of corn and several common spectral vegetation indices, determined functions of principle component analysis （PCA） in LAI inversion. Firstly, the correlation between LAI of corn and spectral vegetation index was set up as highest principle, a variety of vegetation indices was selected on remote sensing by using MATLAB programming software, and the band combination are： NDVI（ 752.4/701.5 ） ,RVI（ 752.4/701.5 ）, MSR（ 752.4/ 701.5） ,SAVI（823.7/701.5）, and MSAVI（ 823.7/701.5 ）. Then PCA was used to analyze these five vegetation indices, LAI- VI multiple regression model was established. Meanwhile, the accuracy of the model was also verified, which was 96. 237%. With the experiment, it＇ s confirmed that the PCA in the inversion of vegetation LAI worked effectively, which could be widely used in the future.
出处
《测绘与空间地理信息》
2015年第9期20-23,共4页
Geomatics & Spatial Information Technology
基金
国家863计划项目(2009AA12Z136)资助
关键词
植被指数
主成分分析
玉米叶面积指数
vegetation index
principal component analysis
maize leaf area index
