冬小麦叶绿素含量高光谱检测技术

Prediction of Chlorophyll Content of Winter Wheat Using Leaf-level Hyperspectral Data

以大田冬小麦叶绿素含量为研究对象,首先利用高光谱成像系统以线扫描方式获取其反射光谱图像,选择感兴趣区域(ROI)并计算出光谱平均反射率值;然后分别针对其原始光谱和一阶差分光谱,通过相关分析和逐步回归分析,得到能反映叶绿素含量变化的7个最佳优化波长;进而基于该优化波长采用多元线性回归(MLR)方法组建模型,通过假设检验剔除对模型贡献不显著的3个波长变量。选用剩余的4个波长即710.85、767.42、650和520 nm作为自变量重新建立模型,基于校正集和预测集模型的决定系数R2分别为0.843 4和0.709 3。研究结果表明,利用高光谱技术检测大田冬小麦叶绿素含量的方法是可行的。

The leaf-level winter wheat hyperspectral response to its chlorophyll content was examined.Firstly,after the 316 scan line images were acquired,the cube image data was constructed and the region of interest（ROI）was selected,then after the average pixel intensity acquired,using correlation analysis combined with stepwise discrimination method for the origin reflective spectrum and the first derivative spectrum,the optimal wavelengths were selected respectively;the chlorophyll content model using multivariate linear regression（MLR） was constructed based on the above seven optimal wavelengths.After statistical significance testing,three wavelengths were abandoned,and the residual four wavelengths,i.e.,710.85,767.42,650 and 520nm were used to construct chlorophyll content prediction model.The prediction results showed that the determination coefficient were R2=0.8434 and R2=0.7093 for the training dataset and the validation dataset respectively.All of these indicated that with the hyperspectral technology,chlorophyll content of winter wheat could be predicted precisely.