Estimation Models for Jujube Leaf Pigment Concentration with Hyperspectrum Data at Canopy Scale
LIU Wei-yang1, PENG Jie1*, DOU Zhong-jiang2, CHEN Bing2, WANG Jia-qiang1, XIANG Hong-ying1, DAI Xi-jun3, WANG Qiong2, NIU Jian-long1
1. College of Plant Science, Tarim University, Alar 843300, China 2. Xinjiang Academy Agricultural and Reclamation Science, Shihezi 832000, China 3. College of Mechanical and Electrical Engineering, Tarim University, Alar 843300, China
Abstract：Plant canopy pigment concentration is a critical variable for agricultural remote sensing due to its close relationship to leaf nitrogen content. The aims of this study were to: (1) compare the prediction performances on chlorophyll, chlorophyll-a and b, and carotenoid concentration in jujube leaf at canopy scale between partial least squares regression (PLSR) and support vector machine (SVM), (2) develop quantitative models to estimate pigment concentration in jujube canopy using hyperspectral data and provide theoretical and technical support for rapidly, non-destructive, less expensive and eco-friendly measuring the concentration. Results from correlation analysis showed that jujube canopy pigment concentration correlated strongly with hyperspectral data. What’s more, the hyperspectral data was better correlated by chlorophyll and chlorophyll-a than chlorophyll-b and carotenoid. Results of independent samples tested in predicting performance indicated that both of the PLSR and SVM models could effectively estimate pigment concentration, however, with different prediction precisions. Additionally, the precision of SVM outperformed PLSR for predicting chlorophyll and carotenoid. Whereas chlorophyll-a and chlorophyll-b were better predicted using PLSR than SVM. Compared among all the pigments’ prediction precisions with corresponding optimal inversion models showed that prediction precisions on chlorophyll, chlorophyll-a and carotenoid were superior to chlorophyll-b. The determination coefficients and residual prediction deviation from predicting chlorophyll, chlorophyll-a and carotenoid were higher than 0.8 and 2.0, respectively, while the mean relative error values were lower than 13%. And the corresponding values from predicting chlorophyll-b were 0.60%, 20.79% and 1.79% respectively.
Key words：Jujube;Pigment;Canopy scale;Visible and near infrared spectrum;Quantitative inversion model
[1] Filella I, Serrano L, Serra J, et al. Crop Science, 1995, 35(5): 1400. [2] WU Wei-mo, NIU Jian-long, WEN Shan-ju, et al. Journal of Tarim University, 2009, 21(4): 61. [3] Wang Wei, Yao Xia, Tian Yongchao, et al. Journal of Integrative Agriculture, 2012, 11(12): 2001. [4] Huang Zhi, Turnera B J, Dury S J, et al. Remote Sensing of Environment, 2004, 93: 18. [5] Knyazikhin Y, Schull M A, Stenberg P, et al. PNAS, 2012, 110: 185. [6] Kokaly R F. Remote Sensing of Environment, 2001, 75: 153. [7] LIU Hong-yu, MAO Han-ping, ZHU Wen-jing, et al(刘红玉, 毛罕平, 朱文静, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2015, 31(Suppl.): 212. [8] HE Jia, LIU Bing-feng, LI Jun(贺 佳, 刘冰锋, 李 军). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(24): 141. [9] ZHANG Yong-he, CHEN Wen-hui, GUO Qiao-ying, et al(张永贺, 陈文惠, 郭乔影, 等). Acta Ecologica Sinica(生态学报), 2013, 33(3): 876. [10] YAO Xia, WU Hua-bing, ZHU Yan, et al(姚 霞, 吴华兵, 朱 艳, 等). Cotton Science(棉花学报), 2007, 19(4): 267. [11] ZHU Xi-cun, ZHAO Geng-xing, WANG Rui-yan, et al(朱西存, 赵庚星, 王瑞燕, 等). Scientia Agricultural Sinica(中国农业科学), 2010, 43(6): 1189. [12] Hunt Jr E R, Doraiswamy P C, McMurtrey J E, et al. International Journal of Applied Earth Observation and Geoinformation, 2013, 21: 103. [13] Daughtry C S T, Walthall C L, Kim M S, et al. Remote Sensing of Environment, 2000, 74: 229.
