基于敏感波段的冬小麦氮素营养高光谱诊断

Hyperspectral Diagnosis of Nitrogen Nutrition in Winter Wheat Based on Sensitive Band

氮素营养状况是作物生长的一个重要参数,准确监测尤为重要。本文利用2013、2014年在北京市农林科学院试验基地的冬小麦叶片反射光谱数据和相应的叶片氮含量及叶片氮累积量数据,采用波段两两组合的方法筛选对叶片氮含量及叶片氮累积量敏感的波段,在各个生育期及全生育期建立冬小麦氮素营养诊断模型。结果表明:(1)波段两两组合筛选出的对叶片氮含量和叶片氮累积量敏感的光谱参数分别为NDSI_((564,728))、NDSI_((543,728))、RSI_((564,728))和RSI_((543,728));(2)在各个生育期和全生育期构建的氮素营养监测模型中,每个生育期的叶片氮含量模型的稳定性和可靠性优于叶片氮累积量的模型,用留一交叉验证法同样表明叶片氮含量模型稳定性和可靠性比较高,研究表明用叶片氮含量可以很好地监测冬小麦氮素营养状况,从而实现对氮肥的精准管理。

Nitrogen nutritional status is an important parameter for crop growth,and how to accurately monitor it is particularly important.In this paper,the winter wheat leaf reflection spectrum data and the corresponding leaf nitrogen content and leaf nitrogen accumulation data at the experimental base of Beijing Academy of Agricultural and Forestry Sciences in 2013-2014 were used to screen out the wave bands which are sensitive to leaf nitrogen content and leaf nitrogen accumulation by the combination of bands,and sensitive wave bands were used to establish nitrogen nutrition diagnosis model of winter wheat in each growth period and whole growth period.The results show that:(1)The sensitive spectral parameters of leaf nitrogen content and leaf nitrogen accumulation screened by the combination of bands are NDSI_((564,728)),NDSI_((543,728)),RSI_((564,728))and RSI_((543,728));(2)Among the nitrogen nutrition diagnosis models constructed in each growth period and the whole growth period,the stability and reliability of LNC in each growth period is better than LNA,and the leave-one-out cross validation method also shows that the accuracy of LNC is relatively higher.This study has shown that the nitrogen content of leaves can be used to monitor the nitrogen nutrition status of winter wheat,so as to achieve precise management of nitrogen fertilizer.