油菜氮素的高光谱特征补偿和组合模型研究

Analysis for High-spectral Features Compensation and Composite Pattern of Rape Nitrogen

[目的]探索油菜氮素光谱分析中水氮交互的解耦方法。[方法]提出了利用反射率特征补偿和组合模型分析法对水分因素对氮素检测的影响进行补偿的方法,并分别建立了氮素光谱分析模型。[结果]利用特征补偿法和模型分类组合分析法进行修正的氮素诊断模型的预测值与实测值的相关系数R分别为0.89和0.91,均方根误差(RMSE)分别为2.94和1.47。[结论]利用模型分类组合分析法能够有效地对水氮交互进行解耦,油菜氮素的定量分析效果较好。

[Objective] The aim of this research was to explore the decoupling method of interaction of water and nitrogen on the spectral analysis of rape nitrogen.[Method] The analysis method of reflectance features compensation and composite pattern was put forward,which can compensate nitrogen detection influenced by water factor.And the spectral analysis models for nitrogen content were respectively established.[Result] The results showed that the correlation coefficient（R） of nitrogen diagnosis models corrected by above-mentioned method was 0.89 and 0.91,and the root mean square error（RMSE） was 2.94 and 1.47.[Conclusion] The interaction of water and nitrogen can be effectively decoupled by the analysis method of composite pattern,which was preferable to the quantitative analysis of rape nitrogen.