Hyperspectral Estimation of Apple Tree Canopy LAI Based on SVM and RF Regression
HAN Zhao-ying1, ZHU Xi-cun1, 2*, FANG Xian-yi1, WANG Zhuo-yuan1, WANG Ling1, ZHAO Geng-xing1, JIANG Yuan-mao3
1. College of Resources and Environment, Shandong Agricultural University, Tai’an 271018, China 2. Key Laboratory of Agricultural Ecology and Environment, Shandong Agricultural University, Tai’an 271018, China 3. College of Horticulture Science and Engineering, Shandong Agricultural University, Tai’an 271018, China
摘要： 叶面积指数(leaf area index，LAI)是反映作物群体大小的较好的动态指标。运用高光谱技术快速、无损地估测苹果树冠叶面积指数，为监测苹果树长势和估产提供参考。以盛果期红富士苹果树为研究对象，采用ASD地物光谱仪和LAI-2200冠层分析仪，在山东省烟台栖霞研究区，连续2年测量了30个果园90棵苹果树冠层光谱反射率及LAI值;通过相关性分析方法构建并筛选出了最优的植被指数;利用支持向量机(support vector machine, SVM)与随机森林(random forests, RF)多元回归分析方法构建了LAI估测模型。新建的GNDVI527，NDVI676，RVI682，FD-NVI656和GRVI517五个植被指数及前人建立的两个植被指数NDVI670和NDVI705与LAI的相关性都达到了极显著水平;建立的RF回归模型中，校正集决定系数C-R2和验证集决定系数V-R2为0.920，0.889，分别比SVM回归模型提高了0.045和0.033，校正集均方根误差C-RMSE、验证集均方根误差V-RMSE为0.249，0.236，分别比SVM回归模型降低了0.054和0.058, 校正集相对分析误C-RPD、验证集相对分析误V-RPD达到了3.363和2.520，分别比SVM回归模型提高了0.598和0.262，校正集及验证集的实测值与预测值散点图趋势线的斜率C-S和V-S都接近于1，RF回归模型的估测效果优于SVM。RF多元回归模型适合盛果期红富士苹果树LAI的估测。
关键词：叶面积指数;高光谱;苹果树;支持向量机;随机森林
Abstract：Leaf area index(LAI) is the dynamic index of crop population size. Hyperspectral technology can be used to estimate apple canopy LAI rapidly and nondestructively. It can be provide a reference for monitoring the tree growing and yield estimation. The Red Fuji apple trees of full bearing fruit are the researching objects. Ninety apple trees canopies spectral reflectance and LAI values were measured by the ASD Fieldspec3 spectrometer and LAI-2200 in thirty orchards in constant two years in Qixia research area of Shandong Province. The optimal vegetation indices were selected by the method of correlation analysis of the original spectral reflectance and vegetation indices. The models of predicting the LAI were built with the multivariate regression analysis method of support vector machine (SVM) and random forest (RF). The new vegetation indices, GNDVI527, NDVI676, RVI682, FD-NVI656 and GRVI517 and the previous two main vegetation indices, NDVI670 and NDVI705, are in accordance with LAI. In the RF regression model, the calibration set decision coefficient C-R2 of 0.920 and validation set decision coefficient V-R2 of 0.889 are higher than the SVM regression model by 0.045 and 0.033 respectively. The root mean square error of calibration set C-RMSE of 0.249, the root mean square error validation set V-RMSE of 0.236 are lower than that of the SVM regression model by 0.054 and 0.058 respectively. Relative analysis of calibrating error C-RPD and relative analysis of validation set V-RPD reached 3.363 and 2.520, 0.598 and 0.262, respectively, which were higher than the SVM regression model. The measured and predicted the scatterplot trend line slope of the calibration set and validation set C-S and V-S are close to 1. The estimation result of RF regression model is better than that of the SVM. RF regression model can be used to estimate the LAI of red Fuji apple trees in full fruit period.
Key words：Leaf area index;Hyperspectral;Apple tree;Support vector machine;Random forests
韩兆迎1，朱西存1,2*，房贤一1，王卓远1，王 凌1，赵庚星1，姜远茂3 . 基于SVM与RF的苹果树冠LAI高光谱估测 [J]. 光谱学与光谱分析, 2016, 36(03): 800-805.
HAN Zhao-ying1, ZHU Xi-cun1, 2*, FANG Xian-yi1, WANG Zhuo-yuan1, WANG Ling1, ZHAO Geng-xing1, JIANG Yuan-mao3. Hyperspectral Estimation of Apple Tree Canopy LAI Based on SVM and RF Regression . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(03): 800-805.
[1] Wiegand C L, Gausman H W, Cuellar J A, et al. Vegetation Density as Deduced from ERTS-1 MSS Response, Proc. Third ETRS-1 Symposium Vol. 1, NASA Technical Reports Server, 1974. 93. [2] Driss H, John R M, Elizabeth P, et al. Remote Sensing of Environment，2004，90：337. [3] LIU Jiao-di, CAO Wei-bin, MA Rong(刘姣娣, 曹卫彬, 马 蓉). Scientia Agricultura Sinica(中国农业科学), 2008(12): 4301. [4] TIAN Yong-chao, YANG Jie, YAO Xia, et al(田永超, 杨 杰, 姚 霞, 等). Chinese Journal of Applied Ecology(应用生态学报), 2009，(7): 1685. [5] YANG Feng, FAN Ya-min, LI Jian-long, et al(杨 峰, 范亚民, 李建龙, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2010，(2): 237. [6] LI Xin-chuan, XU Xin-gang, BAO Yan-song, et al(李鑫川, 徐新刚, 鲍艳松, 等). Scientia Agricultura Sinica(中国农业科学), 2012, 45(17): 3486. [7] HUANG Chun-yan, LIU Sheng-li, WANG Deng-wei, et al(黄春燕, 刘胜利, 王登伟, 等). Soybean Science(大豆科学), 2008，(2): 228. [8] WANG Hong-yan, LI Xiao-song, ZHANG Jin, et al(王红岩, 李晓松, 张 瑾, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013，33(10): 2803. [9] XIA Tian, WU Wen-bin, ZHOU Qing-bo, et al(夏 天, 吴文斌, 周清波, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013，(3): 147. [10] ZHU Xi-cun, ZHAO Geng-xing, LEI Tong(朱西存, 赵庚星, 雷 彤). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2009, 25(12): 190. [11] Gitelson A A, Kaufman Y J, Merzlyak M N. Remote Sensing of Environment, 1996, 58(3): 289. [12] Cristianini N, Taylor J S. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods(支持向量机导论). Translated by LI Guo-zheng, WANG Meng, ZENG Hua-jun(李国正, 王 猛, 曾华军, 译). Beijing: Publishing House of Electronics Industry(北京: 电子工业出版社), 2004. [13] ZHANG Xue-gong(张学工). Acta Automatica Sinica(自动化学报), 2000, 26(1): 32. [14] Breiman L. Machine Learning，2001，45(1): 5. [15] Alexander J D, Butler B J, Hummel J W. Soil Science Society of America Journal, 1980, 44(6): 1282. [16] Vogelmann J E, Rock B N, Moss D M. International Journal of Remote Sensing, 1993, 14(8): 1563. [17] Gupta R K, Vijayan D, Prasad T S. Advances in Space Research, 2001, 28(1): 201. [18] Marshak A, Knyazikhin Y, Davis A, et al. Geophysical Research Letters, 2000, 27(12): 1695. [19] Gitelson A, Merzlyak M N. Journal of Plant Physiology, 1994, 143: 286. [20] Merzlyak M N, Gitelson A A, Chivkunova O B, et al. Physiologia Plantarum, 1999, 106(1): 135. [21] Peuelas J, Piologaya R, Filella I. International Journal of Remote Sensing, 1997, 18(13): 2869. [22] FANG Kuang-nan, WU Jian-bin, ZHU Jian-ping, et al(方匡南, 吴见彬, 朱建平, 等). Statistics & Information Forum(统计与信息论坛), 2011, 26(3): 32.
