基于氮素叶绿素关系的冬小麦籽粒蛋白质含量高光谱反演

Estimation Grain Protein Content of Winter Wheat Based on the Relationship between Nitrogen and Chlorophyll by Hyperspectral Data

为进一步提高光谱数据反演小麦籽粒蛋白质含量的精度以及反演模型的可解释性,研究以籽粒蛋白质含量(GPC)-氮素-叶绿素之间的关系为载体,通过叶绿素筛选相关植被指数,采用偏最小二乘回归(PLS)方法建立GPC反演模型。结果表明,开花期是监测籽粒蛋白质含量的最优时期。开花期氮素与对应密度叶绿素的相关性较高。通过筛选出与叶绿素密切相关的植被指数,利用PLS建立籽粒蛋白质含量反演模型,模型决定系数R2为0.77,RMSE为0.95%,用其他年份数据进行模型验证,结果显示RMSE达到1.22%。本研究表明:基于氮素、叶绿素关系建立PLS反演模型能够实现不同年份GPC光谱遥感反演,且模型在年际间表现出较高的精度和稳定性。

More works were needed to increase the accuracy and interpretability of prediction model of wheat grain protein content. The research based on the relationships between GPC- nitrogen- chlorophyll, selecting proper vegetation index by chlorophyll and using partial least squares regression （PLS） method to build monitor model. The results show that flowering period is the optimal period for GPC monitoring. At flowering stage, there is a high correlation between nitrogen and chlorophyll with the corresponding density. Five indexes are chosen to build the model to calculating GPC by chlorophyll. Coefficient of determination is 0. 77,RMSE is 0. 95%. For validating the model by the data of other year, RMSE is 1.22%. The model shows high precision and stability in different years.