Journal of Integrative Agriculture ›› 2023, Vol. 22 ›› Issue (7): 2248-2270.DOI: 10.1016/j.jia.2023.02.022

• • 上一篇    下一篇

一种基于无人机多光谱影像改进小麦冠层氮素含量估算的双层模型

  

  • 收稿日期:2022-09-08 接受日期:2022-11-20 出版日期:2023-07-20 发布日期:2022-11-20

A double-layer model for improving the estimation of wheat canopy nitrogen content from unmanned aerial vehicle multispectral imagery

LIAO Zhen-qi1, DAI Yu-long1, WANG Han1, Quirine M. KETTERINGS2, LU Jun-sheng1, ZHANG Fu-cang1, LI Zhi-jun1, FAN Jun-liang1#   

  1. 1 Key Laboratory of Agricultural Soil and Water Engineering in Arid and Semiarid Areas of the Ministry of Education, Northwest A&F University, Yangling 712100, P.R.China 

    2 Department of Animal Science, Cornell University, Ithaca, NY 14853, USA

  • Received:2022-09-08 Accepted:2022-11-20 Online:2023-07-20 Published:2022-11-20
  • About author:LIAO Zhen-qi, E-mail: nwafulzq@126.com; #Correspondence FAN Jun-liang, E-mail: nwwfjl@163.com
  • Supported by:
    This study was funded by the Key Research and Development Program of Shaanxi Province of China (2022NY-063) and the Chinese Universities Scientific Fund (2452020018).

PDF

摘要：

准确、快速地估算作物冠层氮素含量（CNC）是精准农业中优化氮肥施用的关键。田间取样测定叶片面积指数（leaf area index，LAI）、冠层光合色素（CPP：包括叶绿素a、叶绿素b和类胡萝卜素）和叶片氮浓度（leaf nitrogen concentration，LNC）费时费力。本文评估了利用高精度无人机多光谱影像估算冬小麦全生育期LAI、CPP和CNC。选取23个光谱特征（5个原始光谱波段、17个植被指数和RGB图像的灰度值）和8个纹理特征（对比度、熵、方差、均值、同质性、相异性、二阶矩、相关性）作为模型的输入，比较了多元逐步回归（MSR）、支持向量回归（SVR）、梯度提升决策树（GBDT）、高斯过程回归（GPR）、反向传播神经网络（BPNN）和径向基函数神经网络（RBFNN）6种机器学习方法反演冬小麦LAI、CPP和CNC的效果。特别提出了一种基于LAI和CPP的双层结构模型来估算CNC。研究结果表明，与仅输入SFs相比，SFs + TFs组合输入大大提高了冬小麦LAI、CPP和CNC的估算精度。RBFNN和BPNN模型在估算冬小麦LAI、CPP和CNC方面优于其他机器学习模型。提出的双层模型（R2=0.67–0.89 , RMSE=13.63–23.71 mg g-1 , MAE = 10.75–7.59 mg g -1）在估算冬小麦CNC时优于传统的直接反演模型（R2=0.61–0.80 , RMSE=18.01–25.12 mg g-1 , MAE = 12.96–18.88 mg g -1）。以SFs + TFs作为输入的双层RBFNN模型在估算冬小麦CNC时精度最高( R2=0.89 , RMSE= 13.63 mg g-1 , MAE=10.75 mg g-1)。本研究可为田间准确、快速地估测冬小麦冠层氮素含量提供指导。

Abstract: The accurate and rapid estimation of canopy nitrogen content (CNC) in crops is the key to optimizing in-season nitrogen fertilizer application in precision agriculture. However, the determination of CNC from field sampling data for leaf area index (LAI), canopy photosynthetic pigments (CPP; including chlorophyll a, chlorophyll b and carotenoids) and leaf nitrogen concentration (LNC) can be time-consuming and costly. Here we evaluated the use of high-precision unmanned aerial vehicle (UAV) multispectral imagery for estimating the LAI, CPP and CNC of winter wheat over the whole growth period. A total of 23 spectral features (SFs; five original spectrum bands, 17 vegetation indices and the gray scale of the RGB image) and eight texture features (TFs; contrast, entropy, variance, mean, homogeneity, dissimilarity, second moment, and correlation) were selected as inputs for the models. Six machine learning methods, i.e., multiple stepwise regression (MSR), support vector regression (SVR), gradient boosting decision tree (GBDT), Gaussian process regression (GPR), back propagation neural network (BPNN) and radial basis function neural network (RBFNN), were compared for the retrieval of winter wheat LAI, CPP and CNC values, and a double-layer model was proposed for estimating CNC based on LAI and CPP. The results showed that the inversion of winter wheat LAI, CPP and CNC by the combination of SFs+TFs greatly improved the estimation accuracy compared with that by using only the SFs. The RBFNN and BPNN models outperformed the other machine learning models in estimating winter wheat LAI, CPP and CNC. The proposed double-layer models (R2=0.67–0.89, RMSE=13.63–23.71 mg g–1, MAE=10.75–17.59 mg g–1) performed better than the direct inversion models (R2=0.61– 0.80, RMSE=18.01–25.12 mg g–1, MAE=12.96–18.88 mg g–1) in estimating winter wheat CNC. The best winter wheat CNC accuracy was obtained by the double-layer RBFNN model with SFs+TFs as inputs (R2=0.89, RMSE=13.63 mg g–1, MAE=10.75 mg g–1). The results of this study can provide guidance for the accurate and rapid determination of winter wheat canopy nitrogen content in the field.

Key words: UAV multispectral imagery ,  spectral features ,  texture features ,  canopy photosynthetic pigment content ,  canopy nitrogen content