基于高光谱的抽穗期寒地水稻叶片氮素预测模型

Prediction Model for Nitrogen Content of Rice Leaves during Heading Stage in Cold Region Based on Hyperspectrum

为快速、无损地监测水稻叶片氮素营养状况,开展了基于高光谱成像技术的抽穗期寒地水稻叶片氮素预测模型的研究。以不同施氮水平的寒地水稻叶片为研究对象,采用连续投影算法(successive projections algorithm,SPA)和分段主成分分析(segmented principal components analysis,SPCA)方法选择水稻叶片的高光谱特征波段,SPCA方法降维后结合相关分析(correlation analysis,CA)构建特征光谱参量,并建立基于全波段高光谱数据、SPA特征波段及SPCA特征光谱参量的多种回归分析模型且对模型进行检验和筛选。研究结果表明:在校正集决定系数RC2上,基于多元逐步回归分析(multiple stepwise regression analysis,MSRA)的全波段模型较好,RC2=0.9 6 4,校正集均方根误差RMSEC=0.083;RP2为0.961,RMSEP为0.050。该研究结果为快速检测水稻叶片氮素含量及水稻生长期间精确施肥管理提供了技术支撑和理论依据。

In order to realize the dynamic, non-destructive diagnosis of rice nitrogen nutritional status, we use hyperspectral imaging techniques as an approach for nitrogen content prediction of rice leaves in cold region. The experiments were carried out for two years (2014 and 2015) at Fangzheng country, Heilongjiang province, China. Longdao 23 was chosen as the test cultivar. 6 nitrogen fertilization rates were applied in our experiments, i.e., N0 (0kg/hm^2 ), N1 (60kg/hm^2 ), N2 (90kg/hm^2 ), N3 (120kg/hm^2 ), N4 (150kg/hm^2 ), and N5 (180kg/hm^2 ). The hyperspectral reflectance and nitrogen content of rice leaves under different nitrogen levels at heading stage were separately measured using American Headwall imaging spectrometer and German AA3 analyzer. Several regression analysis (RA) estimate models have been built based on different characteristic spectral parameters using different algorithms which include successive projections algorithm (SPA) and segmented principal components analysis (SPCA) combined with correlation analysis (CA) for testing and screening. The first method, a nitrogen content value estimation model based on multiple stepwise regression analysis (MSRA) in the whole wavelength region of 400~1000nm has been built and been predicted. We predicted all the estimate models so that testing its accuracy and stability. The results indicated that, reflectance of rice leaves decreases in the visible region, and increases in the near infrared region, with the raise of nitrogen level. From the calibration performance index, the whole wavelength model based on MSRA is the best with a coefficient of determination (RC^2 =0.0964) and root mean square error (MRSEC) of 0.083 and a coefficient of determination (RP^2 = 0.961 ) and the root mean square error (RMSEP) of 0.050. The study provides technical support and theoretical basis for the rapid detection of nitrogen content in rice leaves and the precise fertilization management during rice growth.