近红外漫反射光谱法测定整粒小麦单株蛋白质含量  

Prediction of Protein Content of Intact Wheat Seeds with Near Infrared Reflectance Spectroscopy(NIRS)

作　　者：王卫东[1] 谷运红[1] 秦广雍[1] 霍裕平[1] 

机构地区：[1]郑州大学物理工程学院河南省离子束生物工程重点实验室,河南郑州450052

出　　处：《光谱学与光谱分析》2007年第4期697-701,共5页Spectroscopy and Spectral Analysis

基　　金：国家"十五"科技攻关项目(2001BA302B-03);国家自然科学基金项目(10505018)资助

摘　　要：应用近红外漫反射光谱技术（波长为1100-2498nm,分辨率为2nm）,以整粒小麦为材料建立适合于小麦单株分析的蛋白质含量分析系统。首先选取籽粒蛋白质含量具有梯度差异的小麦样品,然后对样品扫描得到原始光谱信息,通过散射校正及数学处理来消除原始光谱噪声,最后分别采用多元线性回归、主成分分析法和偏最小二乘法法建立回归方程。结果表明,优化各项参数后,光谱经过标准乘性散射校正和一阶导数处理后,回归分析采用修正的偏最小二乘法（MPLS）得到的定标模型效果最佳。最终得到的预测方程定标相关系数（RSQ）、交叉验证标准误差（SECV）、交叉验证相关系数（1-VR）分别为0.94,0.42,0.87。数学模型经过验证样品集检验,预测相关系数达到0.88。该模型达到了快速、无损分析单株小麦的要求,非常适合于品质育种的早代选择。In the present article, the measurement of intact wheat seeds＇ protein content with near infrared reflentance spectroscopy（NIRS） was studied. The wavelength range of 1 100-2 498 nm was used. The distinguishability of NIRS machine was 2 nm, Firstly the representative wheat samples with different protein contents were selected and the original spectra of wheat were obtained using NIRS machine. Then through scatter correction and maths treatment, spectrum noise were decreased. Finally regression methods used multiple linear regression, principal component regression and modified partial least squares respectively. The result showed that after optimizing all the factors, the best calibration model of equation was chosen using ＂first derivative＂ ＋＂Standard Multiplicative Scatter Correction, SMSC＂＋＂Modified Partial Least Squares, MPLS＇. RSQ, SECV and 1-VR of the obtained calibration model were 0. 94, 0. 42 and 0. 87 respectively. A set of representative individual wheat samples were uesed to check the model, and prediction coefficient of determination was 0. 88. Protein content of wheat could be preidicted quickly and scathelessly by using the NIRS measurement. It was feasible to be used in early generation selection in wheat quality breeding process.

关 键 词：整粒小麦 蛋白质含量 近红外漫反射光谱 单株种子 

分 类 号：S511[农业科学—作物学]