基于高光谱指数的林农复合系统小麦冠层氮含量估算研究

Research of the hyperspectral vegetation in deices for the estimation of the nitrogen content of wheat canopy in agro-forestry system

以杨树-小麦间作系统为研究对象,采用Field Spec Pro FR2500地物光谱仪采集的小麦叶层光谱180份,选取基于单作麦田冠层氮含量估测模型中精度较高的9个指数用于估测林农复合系统中小麦冠层氮的含量,探讨不同水平枯落物覆盖量、林分密度、施肥量条件下小麦叶层氮含量的光谱特征。随机选取116份样本作为训练集基以9个指数分别建立估测模型,其余48份样本作为预测集对估测模型进行适应性检验。结果表明:FDNDNI、SDr-SDb两种指数的P-R2与C-R2达到了0.839、0.777与0.844、0.758,此系统预测杨麦间作系统中小麦叶片冠层的氮含量的精度较高,其余7个指数预测精度不理想。以9个指数所建立的估测模型的精度均低于其对单作麦田氮含量的估测精度。

This paper focused on the agro.forestry system, using FieldSpec Pro FR2500 for collecting 180 spectral data samples of wheat leaves from jointing stage to booting stage in the research, selecting nine hyperspectral vegetation indices from estimation model of monoculture crop canopy nitrogen content to estimate the nitrogen content of wheat cano.py in agro.forestry system. Randomly selected 116 samples as the training set to establish estimation model based on nine indices, and the other 48 samples as the prediction set to establish estimation model for adaptive test of estimation model. The results showed that P-R2 of FN-NDNI reached to 0.839, 0.777 and C-R2 of SDr-SDb reached to 0.844, 0.758, which estimate the nitrogen content of wheat leaves in poplar.wheat intercropping ecosystem accurately, and the predic.tion accuracy of the remaining seven indices was not ideal. The prediction accuracy of the estimation model established by nine indices were all lower than in monoculture crop nitrogen content.