Estimating an apple tree canopy nitrogen contents using hyperspectral techniques is important in theoretical and realistic significance for fertilization and management.Taking 80 Fuji apple trees at the early fruiting...Estimating an apple tree canopy nitrogen contents using hyperspectral techniques is important in theoretical and realistic significance for fertilization and management.Taking 80 Fuji apple trees at the early fruiting stage as the research objects,the hyperspectral characteristics of the apple canopy were analyzed systematically.The apple canopy hyperspectral and the canopy nitrogen contents were measured respectively.The canopy hyperspectral characteristics under different nitrogen contents were analyzed and selected the sensitive wave bands.The apple canopy nitrogen content monitoring models were established by using multiple regression method,robust regression and BP neural network method.The results showed that the canopy hyperspectral reflectance had obvious differences under different nitrogen contents.The sensitive bands concentrate on 724~1136 nm.Estimation models based on hyperspectral indices are not ideal.Models based on robust regression(M regression)and BP neural network are better than multiple statistical model,and the accuracy of the BP neural network monitoring model is the best.The results of the study provide a certain reference for estimating apple nutrition using hyperspectral technology.展开更多
文摘Estimating an apple tree canopy nitrogen contents using hyperspectral techniques is important in theoretical and realistic significance for fertilization and management.Taking 80 Fuji apple trees at the early fruiting stage as the research objects,the hyperspectral characteristics of the apple canopy were analyzed systematically.The apple canopy hyperspectral and the canopy nitrogen contents were measured respectively.The canopy hyperspectral characteristics under different nitrogen contents were analyzed and selected the sensitive wave bands.The apple canopy nitrogen content monitoring models were established by using multiple regression method,robust regression and BP neural network method.The results showed that the canopy hyperspectral reflectance had obvious differences under different nitrogen contents.The sensitive bands concentrate on 724~1136 nm.Estimation models based on hyperspectral indices are not ideal.Models based on robust regression(M regression)and BP neural network are better than multiple statistical model,and the accuracy of the BP neural network monitoring model is the best.The results of the study provide a certain reference for estimating apple nutrition using hyperspectral technology.
基金ACKNOWLEDGMENT This paper was supported by Shandong Province Natural Science Fund (ZR2012DM007), the National Nature Science Foundation of China (41271369) and Youth science and technology innovation fund of Shandong Agricultural University (23731).