利用近红外光谱分析预测紫花苜蓿干草品质

Quality Evaluation of Alfalfa Hay by the Spectroscopic Analysis of Near Infrared Reflectance

粗蛋白（CP）、中性洗涤纤维（NDF）和酸性洗涤纤维（ADF）的含量是评价苜蓿（Medicago sativa）产品质量的重要指标。美国现行较多的是使用相对饲用价值（RFV）评估粗饲料产品的质量,我国则用粗饲料分级指数（GI）来评估粗饲料产品的质量。应用偏最小二乘法（PLS）、傅里叶变换近红外光谱技术,建立了适合不同收获期（现蕾期至盛花期）的CP,ADF,NDF,RFV和G1的近红外预测模型。结果表明：粗蛋白的交互验证决定系数（R（cv）2）为0.9129,外部验证中预测决定系数为0.901,模型准确性最高。CP,ADF,NDF,RFV和GI外部验证RPD均大于2.5。本文首次探索紫花苜蓿品质评价指标的模型建立,以期为紫花苜蓿品质育种提供数字依据。

The contents of crude protein（CP）,neutral detergent fiber（NDF）,acid detergent fiber（ADF）are used as important factors to evaluate the hay quality of harvested alfalfa.Relative feed value（RFV） is used to evaluate the quality of feed in America,but forage grading index（GI） is used in China.The quality parameters of alfalfa hay including CP,NDF,ADF,RFV,GI were predicted using fourier transform near infrared reflectance spectroscopy with PLS regression in this test.Then five models were validated by cross validation and external validation.Results indicated that the FT-NIR models of alfalfa hay quality had considerable accuracy and precision.The correlation coefficient of cross validation of CP was 0.9129.The correlation coefficient of external-validation is 0.901.Therefore,FT-NIR can be used to determine the quality of alfalfa hay rapidly and accurately without any chemical reagent.