基于高光谱的枣树叶片氮素表征方法
CSTR:
作者:
作者单位:

1.塔里木大学信息工程学院/塔里木绿洲农业人工智能教育部重点实验室培育基地,阿拉尔 843300;2.塔里木大学南疆特色果树高效优质栽培与深加工技术国家地方联合工程实验室,阿拉尔 843300

作者简介:

李旭,E-mail:lixu2866@126.com

通讯作者:

白铁成,E-mail:9550572@qq.com

中图分类号:

S562;S127

基金项目:

国家自然科学基金项目(41561088);新疆生产建设兵团创新创业平台建设项目(2019CB001);兵团科技创新人才计划(2021CB041);阿拉尔市科技计划(2021GX02);南疆特色果树高效优质栽培与深加工技术国家地方联合工程实验室开放课题(FE201805)


Method for characterizing nitrogen in jujube leaves based on hyperspectral analysis
Author:
Affiliation:

1.Institute of Information Engineering, Tarim University/Incubation Base of Ministry of Education Key Laboratory of Agricultural Artificial Intelligence, Tarim Oasis, Alar 843300, China;2.National Local Joint Engineering Laboratory of High-Efficiency and High-Quality Cultivation and Deep Processing Technology of Southern Xinjiang Special Fruit Trees, Tarim University, Alar 843300, China

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    为提高枣树种植过程中施用氮肥的精准性,本研究以南疆重要经济作物骏枣Ziziphus jujuba Mill.为研究对象,通过对枣树叶片原始光谱和一阶微分光谱与全氮含量的相关性进行分析,利用光谱敏感变量构建植被指数作为衍生变量,再以衍生变量作为变量建立多种线性和非线性的氮素含量预测模型,并对氮素含量预测模型进行精度检验。结果显示:基于枣树原始光谱和一阶微分光谱的模型拟合决定系数均大于0.75,原始光谱变量的预测效果整体好于一阶微分光谱;预测效果最好的是基于原始光谱变量4的幂函数模型:Nit =1.097x0.735R2为0.821,RMSE为0.024 5。研究表明,建立的氮素含量预测模型能够实现基于高光谱反射率特征对枣树氮素的较好监测效果,能够作为枣树营养素诊断的重要理论依据。

    Abstract:

    Jujube as one important economic crop in Southern Xinjiang was used to analyze the relationship between raw spectra and first-order differential spectra of jujube leaves and the content of total nitrogen with hyperspectral techniques. A model for predicting the content of nitrogen was established to provide a theoretical basis for nitrogen monitoring and precise fertilization during jujube cultivation. Spectral sensitive variables were used to construct vegetation indices as derivative variables. Multiple linear and nonlinear models for predicting the content of nitrogen were established using derivative variables as variables. The accuracy of models for predicting the content of nitrogen was tested. Results showed that the fitted decision coefficients of models based on the original spectra and first-order differential spectra of jujube trees were greater than 0.75. The overall prediction performance of the original spectral variables was better than that of first-order differential spectra. The best prediction was based on the power function model of the original spectral variables 4: Nit =1.097x0.735R2=0.821, and RMSE=0.024 5. It is indicated that the model established for predicting the content of nitrogen can achieve good effect of monitoring nitrogen in jujube tree based on hyperspectral reflectance characteristics, and can serve as an important theoretical basis for the nutrient diagnosis of jujube tree.

    表 1 基于敏感变量构建的植被指数表Table 1 Vegetation index table based on sensitive variables
    表 3 模型的精度参数检验Table 3 Test of the fitting precision parameter of the model
    图1 枣树叶片原始光谱曲线Fig.1 Original spectral reflection curve of jujube leaves
    图2 枣树叶片光谱与全氮含量相关系数Fig.2 Correlation coefficient between spectra and total nitrogen content of jujube leaves
    图3 归一化植被指数相关图像Fig.3 Normalized difference vegetation index related images
    图4 较高精度模型的拟合检验Fig.4 The fitting test of high precision model
    图5 支持向量回归模型拟合检验Fig.5 Support vector regression model fitting test
    表 2 基于植被指数构建的模型Table 2 Model based on vegetation index
    参考文献
    相似文献
    引证文献
引用本文

李旭,石子琰,刘伟,白铁成,吴翠云,张宇阳,邬竞明.基于高光谱的枣树叶片氮素表征方法[J].华中农业大学学报,2023,42(3):203-210

复制
分享
文章指标
  • 点击次数:616
  • 下载次数: 690
  • HTML阅读次数: 91
  • 引用次数: 0
历史
  • 收稿日期:2022-10-17
  • 在线发布日期: 2023-06-20
文章二维码