Study on Rice Yield Estimation Model Based on Quantile Regression

作     者：Su Zhong-bin Yan Yu-guang Jia Yin-jiang Sun Hong-min Dong Shou-tian Cao Yu-ying 

作者机构：College of Electrical and InformationNortheast Agricultural UniversityHarbin 150030China 

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

年 卷 期：2020年第27卷第2期

页      面：136-143页

学科分类：082804[工学-农业电气化与自动化] 08[工学] 0828[工学-农业工程] 09[农学] 0903[农学-农业资源与环境] 0901[农学-作物学] 

基　　金：Supported by the National Key R&D Program of China(2016YFD020060305) 

主　　题：quantile regression multispectral image rice yield vegetation index 

摘      要：An airborne multi-spectral camera was used in this study to estimate rice *** experimental data were achieved by obtaining a multi-spectral image of the rice canopy in an experimental field throughout the jointing stage(July,2017)and extracting five vegetation *** indices and rice growth parameter data were compared and *** predictors were screened by using significance analysis and quantile and ordinary least square(OLS)regression models estimating rice yields were *** results showed that a quantile regression model based on normalized difference vegetation indices(NDVI)and rice yields performed was best forτ=0.7 ***,NDVI was determined as an effective variable for the rice yield estimation during the jointing *** accuracy of the quantile regression estimation model was then assessed using RMES and MAPE test *** yields by this approach had better results than those of an OLS regression estimation model and showed that quantile regression had practical applications and research significance in rice yields estimation.