浙江农业科学 ›› 2024, Vol. 65 ›› Issue (10): 2323-2337.DOI: 10.16178/j.issn.0528-9017.20230980

• 现代农业与机械化 • 上一篇    下一篇

无人机高光谱数据的辣椒SPAD值反演

王宇1(), 杨坤2,*(), 饶维冬1, 冯第飞1, 汪泓3, 肖玖军4, 张胜国1   

  1. 1.中国电建集团 贵阳勘测设计研究院有限公司,贵州 贵阳 550081
    2.贵州省测绘资料档案馆,贵州 贵阳 550004
    3.贵州大学 矿业学院,贵州 贵阳 550025
    4.贵州科学院 山地资源研究所,贵州 贵阳 550001
  • 收稿日期:2023-10-08 出版日期:2024-10-11 发布日期:2024-10-25
  • 通讯作者: 杨坤(1974—),男,正高级工程师,硕士,主要从事地理信息应用与卫星遥感技术应用,E-mail:413135739@qq.com
  • 作者简介:王宇(1998—),女,助理工程师,硕士,主要从事农业摄影测量研究,E-mail:2029807592@qq.com
  • 基金资助:
    国家重点研发计划(2017YFD0101702);贵州省科技支撑计划(黔科合支撑〔2020〕1Y172号);贵州省科技支撑计划(黔科合支撑〔2021〕1Y173号);贵州省科技支撑计划(黔科合支撑〔2021〕一般496号);遥感大数据智能挖掘与应用服务关键技术研究(黔科合重大专项〔2022〕001)

Inversion of pepper SPAD values from UAV hyperspectral data

WANG Yu1(), YANG Kun2,*(), RAO Weidong1, FENG Difei1, WANG Hong3, XIAO Jiujun4, ZHANG Shengguo1   

  1. 1. China Power Construction Group Guiyang Survey and Design Research Institute Co., Ltd., Guiyang 550081, Guizhou
    2. Guizhou Provincial Surveying and Mapping Data Archives, Guizhou 550004, Guiyang
    3. School of Mining, Guizhou University, Guiyang 550025, Guizhou
    4. Institute of Mountain Resources, Guizhou Academy of Sciences, Guiyang 550001, Guizhou
  • Received:2023-10-08 Online:2024-10-11 Published:2024-10-25

摘要:

为了建立更加稳定、预测能力更强的辣椒叶绿素含量反演模型,该研究基于无人机高光谱数据和实测叶绿素相对含量(SPAD值),分别利用原始光谱及其他变换光谱与SPAD值进行相关性分析,用最大相关系数法(MCC)选取相关性较好的特征波段生成特征波段数据集,再用遗传算法-偏最小二乘法(GAPLS)进行降维得到最优特征波段组合,采用偏最小二乘法(PLSR)、反向传播神经网络(BPNN)、随机森林(RF)、最小二乘支持向量机(LSSVM)和遗传算法优化的最小二乘支持向量机(GA-LSSVM)5种机器学习算法构建辣椒叶绿素含量反演模型。结果表明:辣椒叶片SPAD值与高光谱反射率成反比;辣椒叶绿素的敏感波段主要集中在400~700 nm;经过一阶微分处理后的光谱与SPAD值相关性最好,671 nm波长下一阶微分光谱与叶绿素含量呈最大负相关,相关系数为-0.69;基于倒数对数光谱建立的模型普遍精度较高;模型中表现最好的为基于微分光谱搭建的GA-LSSVM模型,其决定系数(R2)、均方根误差(RMSE)和相对分析误差(RPD)值分别为0.84、1.41、2.24,其次是基于倒数对数光谱的RF模型,其R2、RMSE和RPD值分别为0.83、1.57、2.13。

关键词: 辣椒, 叶绿素, 冠层叶片, 无人机高光谱, 组合算法

Abstract:

In order to establish a more stable and predictive inversion model of chlorophyll content in pepper, this study analyzed the correlation between the original spectrum and other transformation spectra and the chlorophyll relative content (SPAD value) based on the UAV hyperspectral data and SPAD value. The maximum correlation coefficient method (MCC) was used to select the feature bands with good correlation to generate the feature band dataset, and then the genetic algorithm-partial least squares method (GAPLS) was used to reduce the dimension to obtain the optimal feature band combination. Five machine learning algorithms, namely partial least squares (PLSR), backpropagation neural network (BPNN), random forest (RF), least squares support vector machine (LSSVM) and genetic algorithm optimized least squares support vector machine (GA-LSSVM), were used to construct a chlorophyll content inversion model of pepper. The results showed that the SPAD value of pepper leaves was inversely proportional to the hyperspectral reflectance. The sensitive band of chlorophyll in pepper was mainly concentrated in 400~700 nm. The first-order differential spectra had the best correlation with the SPAD value, and the second-order differential spectra at 671 nm wavelength had the largest negative correlation with chlorophyll content, with a correlation coefficient of -0.69. The models based on reciprocal logarithmic spectra generally had high accuracy. The best performance of the model was the GA-LSSVM model based on differential spectroscopy, with the coefficient of determination (R2), root mean square error (RMSE) and relative analysis error (RPD) values of 0.84, 1.41 and 2.24, respectively, followed by the RF model based on reciprocal logarithmic spectroscopy, with R2, RMSE and RPD values of 0.83, 1.57 and 2.13, respectively.

Key words: pepper, chlorophyll, canopy leaf, UAV hyperspectral, combined algorithm

中图分类号: