摘要
苹果叶片氮(N)素含量是反映其生长质量高低的重要因素。利用高光谱遥感技术对苹果叶片N素含量进行定量化反演,可为苹果树的信息化管理提供理论依据。首先使用ASD Field Spec 3地物光谱仪对样点的苹果叶片的N素含量进行测定,得到苹果叶片样品的高光谱反射率及其N素含量;然后在分析苹果叶片原始光谱和一阶导数以及各种变换后光谱特征的基础上,与苹果叶片的N素含量进行多元逐步回归分析,筛选出对N素变化敏感的波段;最后运用BP人工神经网络算法构建敏感波段与N素含量的反演模型,并对模型进行优选和检验,为测定苹果叶片N素含量提供了1个简单可靠的方法。
Nitrogen( N) content of apple leaves is an important indicator for estimating growth status of apple tree.Quantitative inversion of the nitrogen content of apple leaves using high spectral technology can provide the theoretical basis for information management of apple tree. In this paper,the hyperspectral reflectance and nitrogen content of apple leaf samples were measured by using ASD Field Spec 3 spectrometer. The authors constructed multiple regression analysis of the relationships between nitrogen content of apple tree leaves and the original spectrum,the first- order derivative and the transformation forms,selected four wavebands which are more sensitive to the nitrogen change,and constructed the retrieval model for nitrogen content of apple leaves using back propagation( BP) artificial neural network( ANN) algorithm. Finally,the model was optimized and tested. The results show that the model is an effective means to improve capability of predicting apple tree nitrogen content based on BP artificial neural network algorithm.
出处
《国土资源遥感》
CSCD
北大核心
2016年第2期67-71,共5页
Remote Sensing for Land & Resources
基金
山东省自然科学基金项目"苹果叶片色素与水分含量的高光谱估测方法与模型研究"(编号:ZR2012DM007)资助
关键词
苹果叶片
高光谱
氮(N)素含量
BP神经网络
apple leaf
hyperspectral
content of nitrogen(N)
back propagation(BP) neural network