冬小麦冠层叶绿素质量分数高光谱遥感反演研究
发布时间：2019-06-24 23:32
【摘要】：叶绿素质量分数是评估冬小麦生长状况和预测产量的重要参数,估算叶绿素质量分数对于冬小麦的生长监测具有重要意义。利用SPAD-502叶绿素仪和SVCHR 1024i型便携式高光谱仪对冬小麦冠层叶绿素质量分数和光谱特征进行田间测量,分别利用回归分析方法和BP神经网络方法搭建冬小麦叶绿素质量分数的估算模型,并将模型估算的叶绿素质量分数与田间实测的叶绿素质量分数进行对比,分析反演精度,从中筛选出精度最高的模型。结果表明:基于BP神经网络的冬小麦冠层叶绿素质量分数估算模型拟合精度要优于其他7种基于植被指数的估算模型,其相关系数(R)为0.961 4,均方根误差(RMSE)为1.875 4,相对误差(RE)为2.815 2%,以及检验方程的决定系数(R~2)为0.704 8,RMSE为1.744 6,RE为2.845 1%。研究结果为估测冬小麦冠层叶绿素质量分数提供参考,从而为冬小麦叶绿素质量分数的实时、快速、无损监测奠定基础。
[Abstract]:Chlorophyll content is an important parameter to evaluate the growth status of winter wheat and predict the yield. It is of great significance to estimate the chlorophyll mass fraction for the growth monitoring of winter wheat. The chlorophyll content and spectral characteristics of winter wheat canopy were measured by SPAD-502 chlorophyll meter and SVCHR 1024i portable high spectrometer. The estimation model of chlorophyll mass fraction of winter wheat was established by regression analysis and BP neural network method, and the chlorophyll mass fraction estimated by the model was compared with the measured chlorophyll mass fraction in the field, and the inversion accuracy was analyzed. The model with the highest accuracy is selected from it. The results showed that the fitting accuracy of the estimation model of chlorophyll content in winter wheat canopy based on BP neural network was better than that of the other seven estimation models based on vegetation index. The correlation coefficient (R) was 0.961, the root mean square error (RMSE) was 1.875 4, the relative error (RE) was 2.815 2%, and the determination coefficient (R 鈮，
本文编号：2505456
[Abstract]:Chlorophyll content is an important parameter to evaluate the growth status of winter wheat and predict the yield. It is of great significance to estimate the chlorophyll mass fraction for the growth monitoring of winter wheat. The chlorophyll content and spectral characteristics of winter wheat canopy were measured by SPAD-502 chlorophyll meter and SVCHR 1024i portable high spectrometer. The estimation model of chlorophyll mass fraction of winter wheat was established by regression analysis and BP neural network method, and the chlorophyll mass fraction estimated by the model was compared with the measured chlorophyll mass fraction in the field, and the inversion accuracy was analyzed. The model with the highest accuracy is selected from it. The results showed that the fitting accuracy of the estimation model of chlorophyll content in winter wheat canopy based on BP neural network was better than that of the other seven estimation models based on vegetation index. The correlation coefficient (R) was 0.961, the root mean square error (RMSE) was 1.875 4, the relative error (RE) was 2.815 2%, and the determination coefficient (R 鈮，
本文编号：2505456
本文链接：https://www.wllwen.com/kejilunwen/nykj/2505456.html
