Nitrogen Estimation Model of Apple Leaves Based on Imaging Spectroscopy

作者：Xin Wen,Xicun Zhu,Shujing Cao,Xiaoyan Guo,Ruiyang Yu,Jingling Xiong,Dongsheng Gao

摘要：Imaging spectrometer was used to measure the spectral data of apple leaves.The spectral reflectance of apple leaves was extracted.The nitrogen content of apple leaves was correlated with the spectral reflectance after SG smoothing first-order differential treatment.The sensitive wavelengths were selected and nitrogen content prediction models were founded.The results showed that the spectral of apple leaves with different concentration gradients were obvious.The higher nitrogen content was,the lower spectral reflectance was.Established estimation models by using the selected SG smooth first-order differential spectral sensitive wavelengths SG-FDR403,SG-FDR469,SG-FDR525,SG-FDR566,SG-FDR650,SG-FDR696,SG-FDR781,SG-FDR851,SG-FDR933.The determined coefficient(R^2)of the partial least squares model was 0.5202.The root mean square error(RMSE)of that was 2.19 and the relative error(RE)of that was 5.89%.The R^2 of the support vector machine(SVM)model was 0.724.The RMSE of that was 1.94,and the RE of that was 5.13%.It is indicated that the SVM model can estimate the nitrogen content of apple leaves effectively.

发文机构：College of Resources and Environment Key Laboratory of Agricultural Ecology and Environment College of Horticulture Science and Engineering

关键词：APPLELEAVESNITROGENHYPERSPECTRALImagingSUPPORTVECTORMachine

分类号： TP[自动化与计算机技术]