摘要: 以油菜叶片为研究对象,利用高光谱成像技术,成功建立了叶绿素相对值SPAD值的预测模型。共采集了160个油菜叶片样本在380~1030 nm范围内的高光谱图像。选择500~900 nm之间的平均光谱作为油菜叶片样本的光谱。利用蒙特卡罗最小二乘法(monte carlo partial least squares, MC-PLS)剔除了13个异常样本,基于剩余的147个样本光谱数据与SPAD测量值进行分析,采用了不同的方法建立了多种预测模型,包括:全光谱的偏最小二乘法(partial least squares, PLS)模型,连续投影算法(successive projections algorithm, SPA)选择特征波长的PLS预测模型,“红边”位置(λred)的简单经验估测模型,三种植被指数R710/R760,(R750-R705)/(R750-R705)和R860/(R550*R708)分别建立的简单经验估测模型,以及基于这三种植被指数的PLS预测模型。建模结果显示,全光谱的PLS模型预测效果最为精确,其预测相关系数rp为0.833 9,预测均方根误差RMSEP为1.52。而使用SPA算法选出的8个特征波长所建立的PLS模型其预测结果可达到与全光谱的PLS模型非常接近的水平,而且在保证一定精度的条件下减少了大量运算,节省了运算时间,大幅提高了建模的速度。而基于红边位置和选择的三种植被指数而建立的简单经验估计模型其预测结果虽与基于全光谱的PLS预测模型有一定差距,但模型简单、运算量小,适合用于对精度要求不高的场合,对后续的便携仪器设备开发有一定的指导作用。
关键词:油菜叶片;高光谱成像;SPAD;PLS;SPA;红边参数;植被指数
Abstract:In the present work, prediction models of SPAD value (Soil and Plant Analyzer Development, often used as a parameter to indicate chlorophyll content) in oilseed rape leaves were successfully built using hyperspectral imaging technique. The hyperspectral images of 160 oilseed rape leaf samples in the spectral range of 380~1030 nm were acquired.Average spectrum was extracted from the region of interest(ROI) of each sample.We chose spectral data in the spectral range of 500~900 nm for analysis. Using Monte Carlo partial least squares(MC-PLS) algorithm, 13 samples were identified as outliers and eliminated. Based on the spectral information and measured SPAD values of the rest 147 samples, several estimation models have been built based on different parameters using different algorithms for comparison,including: (1) a SPAD value estimation model based on partial least squares(PLS) in the whole wavelength region of 500~900 nm; (2) a SPAD value estimation model based on successive projections algorithmcombined with PLS(SPA-PLS); (3) 4 kind of simple experience SPAD value estimation models in which red edge position was used as an argument; (4) 4 kind of simple experience SPAD value estimation models in which three vegetation indexes R710/R760,(R750-R705)/(R750-R705) and R860/(R550×R708), which all have been proved to have a good relevance with chlorophyll content, were used as an argument respectively; (5) a SPAD value estimation model based on PLS using the 3 vegetation indexes mentioned above. The results indicate that the optimal prediction performance is achieved by PLS model in the whole wavelength region of 500~900 nm, which has a correlation coefficient(rp) of 0.833 9 and a root mean squares error of predicted(RMSEP) of 1.52. The SPA-PLS model can provide avery close prediction result while the calibration computation has been significantly reduced and the calibration speed has been accelerated sharply. For simple experience models based on red edge parameters and vegetation indexes, although there is a slight gap between theprediction performance and that of the PLS model in the whole wavelength region of 500~900 nm, they also have their own unique advantages which should be thought highly of: these models are much simpler and thus the calibration computation is reduced significantly, they can perform an important function under circumstances in which increasing modeling speed and reducing calibration computation operand are more important than improving the prediction accuracy, such as the development of portable devices.
Key words:Oilseed rape leaf;Hyperspectral imaging;SPAD;PLS;SPA;Red edge parameter;Vegetation index
[1] Vane G, Alexander F H G. Remote Sensing of Environment, 1993, 44(2): 117. [2] Scott C C, Hector J B. Agronomy Journal, 1997, 89(4): 557. [3] Peng S, Garcia F V, Laza R C, et al. Agronomy Journal, 1993, 85(5): 987. [4] Horler D N H, Barber J, Barringer A R. International Journal of Remote Sensing, 1980, 1(2): 121. [5] Curran P J, Dungan J L, Gholz H L. Tree Physiology, 1990, 7(1-4): 33. [6] Zou X, Shi J, Hao L, et al. Analytica Chimica Acta, 2011, 706: 105. [7] LIU Fei, NIE Peng-cheng, HE Yong, et al.(刘 飞, 聂鹏程, 何 勇, 等). Science China Information Sciences(中国科学:信息科学), 2011, 54(3): 598. [8] Guo W L, Du Y P, Zhou Y C, et al. World J. Microbiol. Biotechnol., 2012, 28: 993. [9] David M H, Edward V T. Analytical Chemistry, 1988, 60(11): 1193. [10] Liu F, Kong W W, He Y. Sensor Letters, 2011, 9(3): 1126. [11] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Chemometr. Intell. Lab., 2001, 57(2): 65. [12] QIAN Hai-bo, SUN Lai-jun, WANG Le-kai, et al(钱海波, 孙来军, 王乐凯, 等). Chinese Agricultural Science Bulletin(中国农学通报), 2011, 27(18): 51. [13] YAO Fu-qi, ZHANG Zhen-hua, YANG Run-ya, et al(姚付启, 张振华, 杨润亚, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2009, 25(Supp. 2): 123. [14] HUANG Wen-jiang, WANG Ji-hua, ZHAO Chun-jiang, et al(黄文江, 王纪华, 赵春江, 等). Remote Sensing Technology and Application(遥感技术与应用), 2003, 18(4): 206. [15] ZHU Xi-cun, ZHAO Geng-xing, JIANG Yuan-mao, et al(朱西存, 赵庚星, 姜远茂, 等). Infrared(Monthly)(红外) , 2011, 32(12): 31. [16] Daniel A S, John A G. Remote Sensing of Environment, 2002, 81: 337. [17] ZHANG Lian-peng, LIU Qin-huo, WANG De-gao, et al(张连蓬, 柳钦火, 王德高, 等). Bulletin of Surveying and Mapping(测绘通报), 2010, 9: 1.