柑橘叶片叶绿素含量高光谱无损检测模型
针对柑橘叶片叶绿素含量的传统化学检测,不仅耗时长且损伤柑橘叶片,还依赖检测者实操技术,无法集成于精细农业中变量喷施农机具的诸多弊端,该文探讨快速无损检测柑橘叶片叶绿素含量方法。以117棵园栽萝岗甜橙树为研究对象,选用ASD FieldSpec 3光谱仪对萌芽期、稳果期、壮果促梢期、采果期共4个生长时期的柑橘叶片进行高光谱反射率采集,并同步采用分光光度法测得叶片的叶绿素含量;以原始光谱及其变换形式作为模型输入矢量,分别在主成分分析(principle component analysis,PCA)降维的基础上利用支持向量机回归(support vector regression,SVR)算法和在...
        Saved in:
      
    
          | Published in | 农业工程学报 Vol. 31; no. 1; pp. 294 - 302 | 
|---|---|
| Main Author | |
| Format | Journal Article | 
| Language | Chinese | 
| Published | 
            华南农业大学工程学院,广州 510642
    
        2015
     国家柑橘产业技术体系机械研究室,广州 510642 华南农业大学南方农业机械与装备关键技术教育部重点实验室,广州 510642  | 
| Subjects | |
| Online Access | Get full text | 
| ISSN | 1002-6819 | 
| DOI | 10.3969/j.issn.1002-6819.2015.01.039 | 
Cover
| Summary: | 针对柑橘叶片叶绿素含量的传统化学检测,不仅耗时长且损伤柑橘叶片,还依赖检测者实操技术,无法集成于精细农业中变量喷施农机具的诸多弊端,该文探讨快速无损检测柑橘叶片叶绿素含量方法。以117棵园栽萝岗甜橙树为研究对象,选用ASD FieldSpec 3光谱仪对萌芽期、稳果期、壮果促梢期、采果期共4个生长时期的柑橘叶片进行高光谱反射率采集,并同步采用分光光度法测得叶片的叶绿素含量;以原始光谱及其变换形式作为模型输入矢量,分别在主成分分析(principle component analysis,PCA)降维的基础上利用支持向量机回归(support vector regression,SVR)算法和在小波去噪的基础上利用偏最小二乘回归(partial least square regression,PLSR)算法对柑橘叶片叶绿素含量进行建模预测,全生长期整体建模的校正集和验证集最佳模型决定系数 R2分别为0.8713和0.8670,均方根误差 RMSE (root-mean-square error)分别为0.1517和0.1544,试验结果表明,高光谱可快速无损地对柑橘叶片叶绿素含量进行精确的定量检测,为柑橘不同生长期的营养监测提供理论依据。 | 
|---|---|
| Bibliography: | chlorophyll;principle component analysis;nondestructive examination;hyperspectrum;citrus leaves;support vector regression;partial least square regression 11-2047/S Traditional methods of obtaining chlorophyll content of citrus leaves require grinding citrus leaves and applying chemical titrations, which would be harmful to citrus trees and time-consuming. Besides, it's difficult to integrate those chemical methods into variable spraying system as a feedback subsystem. In this paper, we discuss several rapid and non-destructive methods in obtaining chlorophyll content of citrus leaves by using hyperspectral analysis system. Hyperspectral technology obtains synchronously spectrum in continuous space, where we can derive crop growth information visually in a non-destructive way. In this paper, the modeling of chlorophyll content of citrus leaves based on the hyperspectrum was discussed. Field experiments were conducted on 117 planted Luogang citrus trees in the Crab Village of Luogang District, Guangzhou City, Gua  | 
| ISSN: | 1002-6819 | 
| DOI: | 10.3969/j.issn.1002-6819.2015.01.039 |