大豆冠层叶片氮含量检测研究——基于无人机多光谱图像  

Study on Nitrogen Content Detection of Soybean Canopy——Based on Multispectral Image of UAV

作　　者：康恺 张伟[1] 贺燕 亓立强 张平[2] Kang Kai;Zhang Wei;He Yan;Qi Liqiang;Zhang Ping(School of Engineering,Heilongjiang Bayi Agricultural Reclamation University,Daqing 163000,China;College of Science,Heilongjiang Bayi Agricultural Reclamation University,Daqing 163000,China)

机构地区：[1]黑龙江八一农垦大学工程学院,黑龙江大庆163000 [2]黑龙江八一农垦大学理学院,黑龙江大庆163000

出　　处：《农机化研究》2024年第2期151-156,共6页Journal of Agricultural Mechanization Research

基　　金：国家现代农业产业技术体系专项(CARS-04-PS30);黑龙江八一农垦大学研究生教学研究项目(YJG201908);黑龙江省大庆市指导性科技项目(zd-2020-64);国家大学生创新创业项目(202110223130)。

摘　　要：为快速获取大豆冠层叶片氮素含量(Leaf Nitrogen Content,LNC)信息,采用无人机获取大豆冠层LNC多光谱影像光谱特征,通过分析光谱变量与LNC的相关性,选出对大豆冠层LNC敏感的光谱变量。利用逐步回归分析方法建立黑河43、龙垦310、龙垦3401在3个关键生育时期(R1、R3、R5)大豆LNC估测模型。研究结果表明:①在3个品种的3个生育期,除R5时期龙垦3401品种外,NDVI与LNC具有高度相关性,说明NDVI可以较好地进行大豆冠层LNC的反演。②在建模的过程中发现,在R1时期龙垦3401、黑河43、龙垦310所建模型的R2和RMSE依次为0.857、0.133,0.845、0.156,0.821、0.187;在R3时期龙垦3401、黑河43、龙垦310所建模型的R2和RMSE依次为0.835、0.204,0.881、0.113,0.849、0.162;在R5时期龙垦3401、黑河43、龙垦310所建模型的R2和RMSE依次为0.835、0.208,0.814、0.215,0.836、0.211。由此表明,利用无人机多光谱遥感图像数据可以很好地监测大豆LNC的空间分布情况。In order to obtain nitrogen content(Leaf nitrogen content,LNC),obtain the characteristics of LNC,select the spectral variables sensitive to LNC of LNC,and establish soybean LNC estimation model of Heihe 43,Longken 310 and Longken 3401 in three key reproductive periods(R1,R3 and R5).The results show that:①During the three reproductive periods of the three breeds,Except for Longken 3401 species in the R5 period,The NDVI is highly correlated with the LNC,It shows that NDVI can perform a better inversion of soybean canopy LNC;②Found in the process of modeling,The R2 and RMSE of Longken 3401,Heihe 43 and Longken 310 were 0.857 and 0.133 respectively;0.845,0.156,and 0.821,0.187;the R2 and RMSE of Longken 3401,Heihe 43 and Longken 310 were 0.835 and 0.204,respectively;0.881,0.113;0.849,0.162;the R2 and RMSE of Longken 3401,Heihe 43 and Longken 310 were 0.835 and 0.208,respectively;0.814,0.215;0.836,0.211.Therefore,the spatial distribution of soybean LNC can be well monitored using UAV multispectral remote sensing image data.

关 键 词：大豆 叶片氮素含量 无人机 多光谱影像 逐步回归 

分 类 号：S252.9[农业科学—农业机械化工程]