论文部分内容阅读
A novel hyperspectral index,first derivative normalized difference nitrogen index (FD-NDNI),was developed to estimate the nitrogen content of wheat canopy by hyperspectral remote sensing technology.Using the fist derivative spectra at 525,570 and 730 nm and the methods of difference,ratio and normalization,12 new hyperspectral indices were eveloped to quantify the nitrogen content of wheat canopy.These indices were then compared with 17 commonly used hyperspectral indices including mNDVI705,mSR and NDVI705.The accuracy of the index FD-NDNIdeveloped was higher than that by the hyperspectral indices commonly used,as indicated by a calibration coefficient ofdetermination (C-R2) of 0.818 and a predicted coefficient of determination (P-R2) of 0.811 of the estimation predicted by FD-NDNI.Furthermore,the prediction accuracy of FD-NDNI was least sensitive to the change of nitrogen content and LAI values among the hyperspectral indices and therefore least affected by the range of sample values and canopy density when used to estimate the chlorophyll content of wheat canopy.An algorithm of the least squares support vectorregression (LS-SVR) was finally used to optimize the FD-NDNI model.When the parameters C and g reached the optimal values of 6.4 and 1.6,respectively,the C-R2 and P-R2 of the model reached 0.846 and 0.838,respectively,which were higher than those of the exponential model,and indicated that the LS-SVR model was more accurate.Using the LS-SVR inversion model,the OMIS image was calculated one pixel by one pixel,and remote sensing mapping for OMIS image was accomplished.And then the inversion and ground-measured values was compared by the method of regression fitting.The R-square and RMSE of the fitting model were 0.721 and 0.421,respectively,indicated the similarity between of inversion value and measured value was high.The results indicated that FD-NDNI was an optimalhyperspectral index to invert wheat canopy nitrogen content,and LS-SVR algorithm was the preferred method for modeling.The results indicated that it was possible to acquire the nitrogen content of wheat by hyperspectra technology with a high accuracy; FD-NDNI was an optimal hyperspectral index for inversion,and LS-SVR algorithm was the preferred method for modeling.