基于离散小波-微分变换算法定量反演火龙果茎枝叶绿素含量的研究  

Quantitative Inversion of Chlorophyll Content in Stem and Branch of Pitaya Based on Discrete Wavelet Differential Transform Algorithm

作　　者：王延仓 李笑芳 李莉婕[5] 李楠[1,4] 姜倩楠 顾晓鹤 杨秀峰[1,4] 林家禄[1,4] WANG Yan-cang;LI Xiao-fang;LI Li-jie;LI Nan;JIANG Qian-nan;GU Xiao-he;YANG Xiu-feng;LIN Jia-lu(North China Institute of Aerospace Engineering,School of Remote Sensing Information Engineering,Langfang065000,China;Langfang Normal University,Langfang 065000,China;National Engineering Research Center for Information Technology in Agriculture,Beijing 100097,China;North China Institute of Aerospace Engineering,Hebei Province Aerospace Remote Sensing Information Processing and Application Collaborative Innovation Center,Langfang065000,China;Institute of Science and Technology Information,Guizhou Academy of Agricultural Sciences,Guiyang 550006,China)

机构地区：[1]北华航天工业学院遥感信息工程学院,河北廊坊065000 [2]廊坊师范学院,河北廊坊065000 [3]北京农业信息技术研究中心,北京100097 [4]河北省航天遥感信息处理与应用协同创新中心,河北廊坊065000 [5]贵州省农业科学院科技信息研究所,贵州贵阳550006

出　　处：《光谱学与光谱分析》2023年第2期549-556,共8页Spectroscopy and Spectral Analysis

基　　金：河北省教育厅科学技术研究项目(QN2019213);国家重点研发计划项目(2016YFD0300609);高分辨率重大专项(30-Y30F06-9003-20/22);北京市农林科学院科技创新能力建设专项(KJCX20170705);国家自然科学基金项目(41401419)资助。

摘　　要：作为一种仙人掌科植物,火龙果植株无叶,主要依靠肉质茎进行光合作用、蒸腾作用等生理功能,火龙果的肉质茎与常见绿叶类植物叶片在组织结构、形态等方面存在明显差异,且二者在植株冠层结构方面也存在明显差异,该差异会直接影响植株冠层光谱特征,进而影响基于与光谱技术的光合色素监测。为探寻提升火龙果茎枝叶绿素含量估测精度的方法,研究以贵州省罗甸县龙坪镇烟山火龙果种植基地为试验区,先采集火龙果茎枝光谱及光谱测定部位的组织,并采用乙醇萃取法测定此组织的叶绿素含量,然后选用传统数学变换、连续小波变换、离散小波变换、离散小波-微分变换方法分别处理分析光谱数据,并采用相关性分析算法提取、筛选敏感特征波段,最后选用偏最小二乘算法构建火龙果茎枝叶绿素含量估测模型,分析结果如下:(1)采用离散小波-微分变换算法,高频信息与低频信息的峰、谷交替依次呈现,且可用信息分部具有较强的稳定性,可用信息随尺度的增加,曲线振幅加大、频率降低。(2)数学变换内的微分变换、连续小波变换、离散小波变换与离散小波-微分变换方法均能明显提升光谱对火龙果茎枝叶绿素含量的敏感性,其中以离散小波-微分变换方法最优,经处理后光谱与火龙果茎枝叶绿素含量的决定系数最高可达0.565(位于H1分解尺度737.5 nm处)。(3)离散小波-微分变换最能有效提升光谱对火龙果茎枝叶绿素含量的估测能力,并且基于离散小波-微分变换H2尺度构建的估测模型为最优模型,其验证精度的R^(2)=0.769,RMSE=0.040,RPD=1.739。研究分析了四类光谱处理算法在提升光谱对火龙果茎枝叶绿素含量敏感性与估测能力方面的效果,表明离散小波-微分变换算法能有效提升光谱对火龙果茎枝叶绿素含量的估测能力,为火龙果茎枝叶绿素含量的无损估测提供了基础技�As a cactus plant,the dragonfruit plant is leafless and mainly relies on succulent stems for physiological functions such as photosynthesis and transpiration.There are obvious differences in tissue structure and morphology between the succulent stems of dragon fruit and the leaves of common green leaves,and there is also obvious differences in plant canopy structure,which will directly affect the spectral characteristics of plant canopy.Furthermore,it affects the monitoring of photosynthetic pigments based on spectral technology.In order to explore the method to improve the estimation accuracy of chlorophyll content in the stem and branch of dragon fruit,taking the planting base of Yanshan dragon fruit in Longping Town,Luodian County,Guizhou Province,as the experimental area,the tissues of the stem branch and branch of dragon fruit were collected and determined by ethanol extraction.The chlorophyll content of the tissue was determined by ethanol extraction.Then the spectral data were processed and analyzed by traditional mathematical transform,continuous wavelet transform,discrete wavelet transform and discrete wavelet-differential transform respectively.The correlation analysis algorithm was used to extract and screen the sensitive feature bands.Finally,the partial least square algorithm is selected to construct the estimation model of chlorophyll content in the stem and branch of dragon fruit.The conclusions were as follows:(1)under the discrete wavelet-differential transform algorithm.The peaks and valleys of high-frequency and low-frequency information appear alternately,and the segments of available information have strong stability.With the increase of scale,the amplitude of the curve increases,and the frequency decreases.(2)the methods of differential transform,continuous wavelet transform,discrete wavelet transform and discrete wavelet-differential transform in mathematical transform can improve the sensitivity of spectrum to chlorophyll content in stem and branch of dragon fruit,among which the method of

关 键 词：火龙果 叶绿素含量 离散小波算法 高光谱 

分 类 号：S667.9[农业科学—果树学]