基于可见-近红外光谱技术的水稻穗颈瘟染病程度分级方法研究  

Study on Disease Level Classification of Rice Panicle Blast Based on Visible and Near Infrared Spectroscopy

作　　者：吴迪[1] 曹芳[1] 张浩[2] 孙光明[1] 冯雷[1] 何勇[1] 

机构地区：[1]浙江大学生物系统工程与食品科学学院,浙江杭州310029 [2]浙江省农业科学院数字农业研究中心,浙江杭州310021

出　　处：《光谱学与光谱分析》2009年第12期3295-3299,共5页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(60605011;30671213);国家科技支撑项目(2006BAD10A04);浙江省2009年度重大科技专项资助

摘　　要：采用Vis-NIR技术对水稻穗颈瘟染病程度分级方法进行了研究。分别基于原始光谱,变量标准化(SNV)预处理后和多元散射校正(MSC)预处理后的光谱,应用无信息变量消除法(UVE)结合连续投影算法(SPA)对Vis-NIR光谱区进行有效波长的选择。选择后的波长作为输入变量建立最小二乘-支持向量机(LS-SVM)模型。结果表明SNV-UVE-SPA建立的LS-SVM模型预测效果最好。通过SNV-UVE-SPA从全波段600个波长中选择了6个最能够反应光谱信息的波长(459,546,569,590,775和981nm)。SNV-UVE-SPA-LS-SVM组合模型对预测集样本预测得到的确定系数(Rp2),预测集的预测标准差(RMSEP)和剩余预测偏差(RPD)分别达到了0.979,0.507和6.580。结果表明,采用Vis-NIR光谱技术对水稻穗颈瘟染病程度进行分级是可行的。通过UVE-SPA得到的有效波长能够很好地代替全波长。Visible and near infrared（Vis-NIR）spectroscopy was used to fast and non-destructively classify the disease levels of rice panicle blast.Reflectance spectra between 325 and 1 075 nm were measured.Kennard-Stone algorithm was operated to separate samples into calibration and prediction sets.Different spectral pretreatment methods,including standard normal variate（SNV）and multiplicative scatter correction（MSC）,were used for the spectral pretreatment before further spectral analysis.A hybrid wavelength variable selection method which is combined with uninformative variable elimination（UVE）and successive projections algorithm（SPA）was operated to select effective wavelength variables from original spectra,SNV pretreated spectra and MSC pretreated spectra,respectively.UVE was firstly operated to remove uninformative wavelength variables from the full-spectrum.Then SPA selected the effective wavelength variables with less colinearity after UVE.Least square-support vector machine（LS-SVM）was used as the calibration method for the spectral analysis in this study.The selected effective wavelengths were set as input variables of LS-SVM model.The LS-SVM model established based on SNV-UVE-SPA obtained the best results.Only six effective wavelengths（459,546,569,590,775 and 981 nm）were selected from the full-spectrum which has 600 wavelength variables by UVE-SPA,and their LS-SVM model＇s performance was further improved.For SNV-UVE-SPA-LS-SVM model,coefficient of determination for prediction set（R2p）,root mean square error for prediction（RMSEP）and residual predictive deviation（RPD）were 0.979,0.507 and 6.580,respectively.The overall results indicate that Vis-NIR spectroscopy is a feasible way to classify disease levels of rice panicle blast fast and non-destructively.UVE-SPA is an efficient variable selection method for the spectral analysis,and their selected effective wavelengths can represent the useful information of the full-spectrum and have higher signal/noise ratio and less colineari

关 键 词：Vis-NIR光谱 水稻穗颈瘟 无信息变量消除法 连续投影算法 变量选择 

分 类 号：O657.3[理学—分析化学]