作者:Tianlin Liu,Xicun Zhu,Xueyuan Bai,Yufeng Peng,Zhongyu Tian,Meixuan Li,Yuanmao Jiang
摘要:The nutrient inversion model of apple leaves was established by spectral analysis technology to provide technical support for the fine management of apple trees.In Shuangquan Town,Changqing District,Jinan City,Shandong Province,the Fuji apple trees with stopping period of spring shoots were taken as research objects.The spectral reflectance and nitrogen content of apple leaves were measured by ASD Field Spec 4 portable ground object spectrometer.Analyzed the correlation between leaf nitrogen content and spectral reflectance.The sensitive wavelengths with high correlation coefficient were select by fractional differential algorithm,and the optimal vegetation index was constructed and screened out.Partial Least Square Regression(PLSR),Support Vector Machine(SVM)and Random Forests(RF)method were used to construct an inversion model of leaf nitrogen content.The results show that the RF model based on fractional differential second-order treatment is the best inversion model for the nitrogen content of leaves during stopping period of spring shoots.The modeling accuracy determination coefficient R2 reached 0.891,RMSE was 0.0841,and RPD was 2.1396.The determination coefficient R2 of the fitting results of the verification set was 0.617,RMSE was 0.1251,and RPD was 1.7105.The inversion model established by RF method is effective in monitoring the nitrogen content in apple leaves,which provides a theoretical basis for monitoring the growth of apple by hyperspectral technology.
发文机构:College of Resources and Environment National Engineering Laboratory for Efficient Utilization of Soil and Fertilizer Resources College of Horticulture Science and Engineering
关键词:AppleTreeStoppingPeriodofSpringShootsNitrogenNutritionRemoteSensingInversion
分类号: F42[经济管理—产业经济]