基于冠层高光谱信息的苹果树花量估测

doi:10.3864/j.issn.0578-1752.2016.18.015

摘要/Abstract

摘要： 【目的】研究基于盛花期冠层高光谱数据的苹果花量估测技术，为植株花果管理和生产力预测技术的建立奠定基础。【方法】以5年生M₉无性系砧木‘米奇嘎啦’苹果（Malus pumila‘Mitch Gala’）、树形为高纺锤形的植株为试材，在盛花期采集植株冠层可见-近红外高光谱图像，人工统计供试植株花量，比对分析基于原始光谱反射率（original reflectance spectra，OS）与Savitzky-Golay平滑法（savitzky-golay smoothing，SG）、正态变量标准化（standardization of normal variables，SNV）、标准化（Normalize）、一阶求导（first derivation，l^stDer）、二阶求导（second derivation，2^ndDer）共5种预处理的高光谱数据的偏最小二乘法（partial least squares method，PLS）模型，以及基于载荷系数法（x-loading weight，x-LW）提取的特征波长的PLS模型、人工神经网络（the back-propagation neural network，BPNN）、最小二乘支持向量机（the least squares support vector machines，LS-SVM）等模型对单株单位面积花量实时估测精度的影响。【结果】苹果树单株花量与单株单位面积花量具有较高的相关系数，表明采用冠层单位面积花量替代单株总花量进行树体花量估测可行。单株单位面积花量与植株冠层光谱反射率在紫外-可见光波长（308—700 nm）呈极显著正相关，在近红外波长（750—1 000 nm）相关性不显著。基于全波长，以Normalize预处理光谱建立的PLS模型对单株单位面积花量的预测效果最好，校正集决定系数（R_c²）和预测集决定系数（R_p²）分别为0.794和0.804，校正集均方根误差（RMSEC）和预测集均方根误差（RMSEP）分别为0.084、0.062，预测相对误差（RE%）为3.940。基于特征波长的BPNN模型稳定性差，而LS-SVM模型的建模效果较好，R_c²和R_p²分别为0.826和0.804，RMSEC和RMSEP分别为0.077、0.064，RE%为12.160。【结论】基于Normalize预处理的PLS模型对高纺锤形苹果树冠层单位面积花量的预测效果最优，同时，本研究利用高光谱成像仪获取的数据，经过分析处理对提取特征信息进行简化，可为多光谱遥感数据的应用提供依据。

关键词: 苹果树, 单位面积花量, 高光谱, 偏最小二乘法, 载荷系数法

Abstract: 【Objective】To study a technology for estimating the number of apple flowers which is based on the hyperspectral image information of a canopy at full-bloom stage, in order to lay a foundation for the establishment of the technologies used for the management and the productivity prediction of the flowers and fruits of a plant. 【Method】 The 5-year-old Malus pumila ‘Mitch Gala’ trees with M₉ clonal rootstocks in the shape of high spindles were studied. The visible and near infrared hyperspectral images of the canopy at full-bloom stage were collected, and the number of the flowers of the trees was selected and then counted manually. Finally, comparatively analyze the effects of the Partial Least Squares (PLS) models based on the original reflectance spectra (OS) and the spectra pretreated by five kinds of methods including savitzky–golay smoothing(SG), standardization of normal variables (SNV), Normalize, first derivation(l^stDer), second derivation(2^ndDer), the PLS, the back-propagation neural network (BPNN) and the least squares support vector machines (LS-SVM) based on characteristic wavelengths obtained by x-loading weight (x-LW) on the accuracy of the real-time estimation of the amount of flowers per unit area per tree. 【Result】 Both the number of flowers per tree and the number of flowers per unit area per tree have high correlation coefficients, which means using the number of flowers per unit area of the canopy as a substitute for the total number of flowers per tree to predict the number of flowers of all the trees is feasible. The number of flowers per unit area per tree had a very significant positive correlation with the reflectivity of the trees’ canopy in the ultraviolet and visible wavelength (308-700 nm), but the correlation between the two was not significant in the near-infrared wavelength (750-1 000 nm). Based on full wavelength, the PLS model based on spectra pretreated by Normalize predicts the number of flowers per unit area per tree most accurately, whose determination coefficients of the calibration sets (R_c²) and of the prediction sets (R_p²) were 0.794 and 0.804, the root-mean-square errors of the calibration sets (RMSEC) and of the prediction sets (RMSEP) were 0.084, 0.062, and whose relative error (RE%) of prediction sets was 3.940. Based on characteristic wavelengths, the stability of BPNN model is bad，the LS-SVM model has better modeling results, with the R_c² and the R_p² being 0.826 and 0.804, RMSEC and the RMSEP being 0.077 and 0.064, the RE% of prediction sets is 12.160. 【Conclusion】 The PLS prediction model based on Normalize pretreatment has the best prediction results of the number of flowers of apple trees in the shape of high spindles per unit area per tree’s canopy, at the same time, after obtaining the spectral data by hyperspectral imager, analysis and processing to extract feature information through simplification, which can provide a basis for the application of multispectral remote sensing data.

Key words: apple tree, flowers per unit area, hyper-spectra, PLS, x-LW

刘颖，王克健，谢让金，吕强，何绍兰，易时来，郑永强，邓烈. 基于冠层高光谱信息的苹果树花量估测[J]. 中国农业科学, 2016, 49(18): 3608-3617.

LIU Ying, Wang Ke-jian, XIE Rang-jin, Lü Qiang, HE Shao-Lan, YI Shi-lai, ZHENG Yong-qiang, DENG Lie. Estimating the Number of Apple Tree Flowers Based on Hyperspectral Information of a Canopy[J]. Scientia Agricultura Sinica, 2016, 49(18): 3608-3617.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2016.18.015

https://www.chinaagrisci.com/CN/Y2016/V49/I18/3608

参考文献

[1] 孙佳佳. 中国苹果进口贸易研究[D]. 杨凌: 西北农林科技大学, 2014.

Sun J J. China apple import trade research [D]. Yangling: Northwest A&F University, 2014. (in Chinese)

[2] 向阳. 浅谈苹果疏花疏果技术. 农业科技与信息, 2013, 19: 29-30.

Xiang Y. Introduction to apple thin flower thinning technology. Journal of Agricultural Science and Technology and Information Technology, 2013, 19: 29-30. (in Chinese)

[3] Nicolaï B M, Theron K I, Lammertyn J. Kernel PLS regression on wavelet transformed NIR spectra for prediction of sugar content of apple. Chemometrics and Intelligent Laboratory Systems, 2007, 85(2): 243-252.

[4] CAVALHO S, SCHLERF M, PUTTEN W H V D, SKIDMORE A K. Hyperspectral reflectance of leaves and flowers of an outbreak species discriminates season and successional stage of vegetation. International Journal of Applied Earth Observation and Geoinformation, 2013, 24: 32-41.

[5] 朱西存, 赵庚星, 王瑞燕, 董芳, 王凌, 雷彤. 苹果叶片的高光谱特征及其色素含量监测. 中国农业科学, 2010, 43(6): 1189-1197.

ZHU X C, ZHAO G X, WANG R Y, DONG F, WANG L, LEI T. Hyperspectral characteristics of apple leaves and their pigment contents monitoring. Scientia Agriculture Sinica, 2010, 43(6): 1189-1197. (in Chinese)

[6] 雷彤, 赵庚星, 朱西存, 董超, 孟岩, 战冰. 基于高光谱的苹果果期冠层光谱特征及其果量估测. 生态学报, 2010, 30(9): 2276-2285.

LEI T, ZHAO G X, ZHU X C, DONG C, MENG Y, ZHAN B. Canopy spectral features and fruit amount estimation of apple tree at fruit stage based on hyperspectral data. Acta Ecologica Sinica, 2010, 30(9): 2276-2285. (in Chinese)

[7] GUTIERREZ M, NORTON R, THORP K R, WANG G. Association of spectral reflectance indices with plant growth and lint yield in upland cotton. Crop Science, 2012, 52(2): 849-857.

[8] 程洪, DAMEROW L, BLANKE M, 孙宇瑞, 程强. 基于树冠图像特征的苹果园神经网络估产模型. 农业机械学报, 2015(1): 4.

CHENG H, DAMEROW L, BLANKE M, SUN Y R, CHEN Q. ANN model for apple yield estimation based on feature of tree image . Transactions of the Chinese Society for Agricultural Machinery, 2015(1): 4. (in Chinese)

[9] PRASAD B, BABAR M A, CARVER B F, RAUN W R, KLATT A R. Association of biomass production and canopy spectral reflectance indices in winter wheat. Canadian Journal of Plant Science, 2009, 89(3): 485-496.

[10] 朱西存, 赵庚星, 雷彤, 李希灿, 陈志强. 苹果花期的冠层高光谱特征研究. 光谱学与光谱分析, 2009, 29(10): 2708-2712.

ZHU X C, ZHAO G X, LEI T, LI X C, CHEN Z Q. Study on hyperspectral characteristics of apple florescence canopy. Spectroscopy and Spectral Analysis, 2009, 29(10): 2708-2712. (in Chinese)

[11] 潘蓓, 赵庚星, 朱西存, 刘海腾, 梁爽, 田大德. 利用高光谱植被指数估测苹果树冠层叶绿素含量. 光谱学与光谱分析, 2013, 33(8): 2203-2206.

PAN B, ZHAO G X, ZHU X C, LIU H T, LIANG S, TIAN D D. Estimation of chlorophyll content in apple tree canopy based on hyperspectral parameters. Spectroscopy and Spectral Analysis, 2013, 33(8): 2203-2206. (in Chinese)

[12] BROGE N H, MORTENSEN J V. Deriving green crop area index and canopy chlorophyll density of winter wheat from spectral reflectance data. Remote sensing of environment, 2002, 81(1): 45-57.

[13] ROYO C, VILLEGAS D. Field measurements of canopy spectra for biomass assessment of small-grain cereals//MATOVIC D. Biomass-Detection, Production and Usage. In Tech, 2011: 87-92.

[14] 尼珍, 胡昌勤, 冯芳. 近红外光谱分析中光谱预处理方法的作用及其发展. 药物分析杂志, 2008, 28(5): 824-829.

NI Z, HU C Q, FENG F. Progress and effect of spectral data pretreatment in NIR analytical technique. Chinese Journal of Pharmaceutical Analysis, 2008, 28(5): 824-829. (in Chinese)

[15] RASMUSSEN J, AAMAND J, ROSENBERG P, JACOBSEN O S, SORENSEN S R. Spatial variability in the mineralisation of the phenylurea herbicide linuron within a danish agricultural field: multivariate correlation to simple soil parameters. Pest Management Science, 2005, 61(9): 829-837.

[16] 岳学军, 全东平, 洪添胜, 王健, 瞿祥明, 甘海明. 柑橘叶片叶绿素含量高光谱无损检测模型. 农业工程学报, 2015, 31(1): 294-302.

YUE X J, QUAN D P, HONG T S, WANG J, QU X M, GAN H M. Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(1): 294-302. (in Chinese)

[17] BARKER M, RAYENS W. Partial least squares for discrimination. Journal of Chemometrics, 2003, 17: 166-173.

[18] ElMASRY G, WANG N, VIGNEAUL C. Detecting chilling injury in red delicious apple using hyperspectral imaging and neural networks. Postharvest Biology and Technology, 2009, 52(1): 1-8.

[19] BALABIN R M, SAFIEVA R Z, LOMAKINA E I. Comparison of linear and nonlinear calibration models based on near infrared (NIR) spectroscopy data for gasoline properties prediction. Chemometrics and Intelligent Laboratory Systems, 2007, 88(2): 183-188.

[20] 李永亮. 杉木红边参数估算叶绿素含量模型研究[D]. 长沙: 中南林业科技大学, 2011.

LI Y L. The Study of estimation models of chinese fir chlorophyll content based on red edge parameters [D]. Changsha: Central South University of F&T, 2011. (in Chinese)

[21] GIOVANELLI G, SINELLI N, BEGHI R, GUIDETTI R, CASIRAGHI E. NIR spectroscopy for the optimization of postharvest apple management. Postharvest Biology & Technology, 2014, 87(1): 13-20.

[22] CLEVERS J G P W, KOOISTRA L, SCHAEPMAN M E. Using spectral information from the NIR water absorption features for the retrieval of canopy water content. International Journal of Applied Earth Observation and Geoinformation, 2008, 10(3): 388-397.

[23] BAUMGARTNER R, SOMORJAI R, BOWMAN C, SORRELL T C, MOUNTFORD C E, HIMMELREICH U. Unsupervised feature dimension reduction for classification of MR spectra. Magnetic Resonance Imaging, 2004, 22(2): 251-256.

[24] 雷彤, 赵庚星, 朱西存, 战冰, 张洋洋. 基于高光谱和数码照相技术的苹果花期光谱特征研究. 中国农业科学, 2009, 42(7): 2481-2490.

LEI T, ZHAO G X, ZHU X C, ZHAN B, ZHANG Y Y. Research of apple florescence spectral features based on hyperspectral data and digital photos. Scientia Agricultura Sinica, 2009, 42(7): 2481-2490. (in Chinese)

[25] HANSEN P M, SCHJOERRING J K. Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote sensing of environment, 2003, 86(4): 542-553.

[26] 张瑶, 郑立华, 李民赞, 邓小蕾, 王诗丛, 张锋, 冀荣华. 基于光谱特征分析的苹果树叶片营养素预测模型构建. 农业工程学报, 2013, 29(8): 171-178.

ZHANG Y, ZHEN L H, LI M Z, DENG X L, WANG S C, ZHANG F, JI R H. Construction of apple tree leaves nutrients prediction model based on spectral analysis. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(8): 171-178. (in Chinese)

[27] 房贤一, 朱西存, 王凌, 赵庚星. 基于高光谱的苹果盛果期冠层叶绿素含量监测研究. 中国农业科学, 2013, 46(16): 3504-3513.

FANG X Y, ZHU X C, WANG L, ZHAO G X. Hyperspectral monitoring of the canopy chlorophyll content at apple tree prosperous fruit stage. Scientia Agricultura Sinica, 2013, 46(16): 3504-3513. (in Chinese)

[28] JONES C L, WEEKLER P R, MANESS N O, JAYASEKARA R, ATONE M L, CHRZ D. Remote sensing to estimate chlorophyll concentration in spinach using multi-spectral plant reflectance. Transactions of the Asabe, 2007, 50(6): 2267-2273.

[29] LEVASSEUR-GARCIA C. Infrared spectroscopy applied to identification and detection of microorganisms and their metabolites on cereals (corn, wheat, and barley)//Agricultural Science. Scientific pesearch, 2012.

[30] BRISCO B, BROWN R J, HIROSE T, MCNAIRN H, STAENZS K. Precision agriculture and the role of remote sensing: a review. Canadian Journal of Remote Sensing, 1998, 24(3): 315-327.

[31] 杨进. 矮砧苹果的发展前景. 中国农业科学, 1983, 16(6): 26-31.

YANG J. Prospect in development of apple trees of dwarf stocks. Scientia Agricultura Sinica, 1983, 16(6): 26-31. (in Chinese)

[32] 刘万亮, 迟乃峰, 徐建波, 宋立龙, 孙兵杰. 苹果的花期管理. 烟台果树, 2008(2): 44.

LIU W L, CHI N F, XU J B, SONG L L, SUN B J. The management of apple in blooming. Yantai Fruits, 2008(2): 44. (in Chinese)

[33] SOLOMAKHIN A A, BLANKE M M. Mechanical flower thinning improves the fruit quality of apples. Journal of the Science of Food and Agriculture, 2010, 90(5): 735-741.

[34] 田喜, 何绍兰, 吕强, 易时来, 谢让金, 郑永强, 廖秋红, 邓烈. 高光谱图像信息的柑橘叶片光合色素含量分析技术研究. 光谱学与光谱分析, 2014(9): 2506-2512.

TIAN X, HE S L, LV Q, YI S L, XIE R J, ZHENG Y Q, LIAO Q H, DENG L. Determination of photosynthetic pigments in citrus leaves based on hyperspectral images datas. Spectroscopy and Spectral Analysis, 2014, (9): 2506-2512. (in Chinese)

[35] 易时来, 邓烈, 何绍兰, 郑永强, 毛莎莎. 锦橙叶片钾含量光谱监测模型研究. 中国农业科学, 2010, 43(4): 780-786.

YI S L, DENG L, HE S L, ZHENG Y Q, MAO S S. A spectrum based models for monitoring leaf potassium content of Citrus sinensis (L) cv. Jincheng orange. Scientia Agricultura Sinica, 2010, 43(4): 780-786. (in Chinese)

[36] 卢艳丽, 白由路, 杨俐苹, 王红娟. 基于高光谱的土壤有机质含量预测模型的建立与评价. 中国农业科学, 2007, 40(9): 1989-1995.

LU Y L, BAI Y L, YANG L P, WANG H J. Prediction and validation of soil organic matter content based on hyperspectrum. Scientia Agricultura Sinica, 2007, 40(9): 1989-1995. (in Chinese)

[37] 汪海燕, 黎建辉, 杨风雷. 支持向量机理论及算法研究综述. 计算机应用研究, 2014, 31(5): 1281-1286.

WANG H Y, LI J H, YANG F L. Overview of support vector machine analysis and algorithm. Application Research of Computers, 2014, 31(5): 1281-1286. (in Chinese)

[38] BASAK D, PAL S, Patranabis D C. Support vector regression. Neural Information Processing-Letters and Reviews, 2007, 11(10): 203-224.