A Prediction Mode of Crop Canopy Nitrogen Hyperspectral Under Mode of "Cornfield Goose Breeding"

作     者：Wang Shu-wen Ma Xin-yu Guo Chun-fei Guo Yong-gang Zhang Yan Zhao Zhong-yuan Wang Chaofan Chen Xiao-liang Liu Jun Li Rui-xuan Li Si-jia Xu kun Gao Jia-ying Wang Run-tao 

作者机构：College of Electric and InformationNortheast Agricultural UniversityHarbin 150030China College of Information EngineeringLingnan Normal UniversityGuangdong 524048China Tibet Agriculture and Animal Husbandry UniversityTibet UniversityLinzhi Tibet860000China 

出 版 物：《Journal of Northeast Agricultural University(English Edition)》 (东北农业大学学报（英文版）)

年 卷 期：2019年第26卷第2期

页      面：75-86页

学科分类：0905[农学-畜牧学] 09[农学] 0901[农学-作物学] 

基　　金：Supported by the National "863" Project(AA2013102303) Heilongjiang Natural Science Foundation Project(C2015006) Tibet Science and Technology Department Project(XZ201703-GC-11) National Key R&D Program of China(2018YFD0201004) China Postdoctoral Fund(2016M601406) Key Cultivation Project of Lingnan Normal University in 2019(LZ1903) 

主　　题：hyperspectral agriculture and animal husbandry integration nitrogen corn canopy 

摘      要：The corn canopy taking in before and after grazing term in the production mode ofcornfield goosewas used as the research *** techniques were used to analyze the spectral characteristics of corn canopy leaves in different periods,and a full-band based Principal Component Regression model,Partial Least Squares Regression model and Support Vector Machine regression model were established to propose a fast,convenient and efficient hyperspectral imaging detection *** results showed that the nitrogen value of the grazing area was always lower than that of the control area,during the grazing period,the reflectance of the near-infrared spectrum increased,and the red edge position moved to the *** terms of model establishment,the optimal model was obtained for different grazing *** positive set determining coefficient(Rc 2),the root-mean-square error correction(RMSEC),the prediction set decision coefficient(Rp 2)and the root-mean-square error prediction(RMSEP)were obtained by using SNV-BICA-PCA-PLS in the pre-grazing *** values were 0.9136,0.1750,0.8910 and 0.1052,*** values of Rc 2,RMSEC,Rp 2 and RMSEP were 0.9006,0.0418,0.8508 and 0.1233,respectively,when they were obtained by using MSC-BICA-PCA-MSC in the post-grazing *** research results provided support and help for the futureagriculture and animal husbandry integrationto optimize production management and establish a nitrogen nutrient balance model.