基于最佳波段判别的湿地植物叶片全氮反演研究.pdfVIP

4840 生态学报 34 卷 in Beiji吨， a typical wetland using reclaimed water. 币le leaf reflectance spectra of main wetland plants were acquired by means of an ASD FieldSpec 3 spectrometer (350一2500nm ). Leaf total nitrogen content was determined by Kjeldahl nitrogen measurement method after acquiring the leaf reflectance spectra. The method ,Give a cross correlation analysis , was used to build the correlations between leaf nitrogen content and the original spectrum , first derivative spectrum. Then , the selected bands were divided into some 缸eas according to QiSeGuang spectral range and the interval of selected bands. Those bands which 町e high frequency 、 frequency more 、 ranked high frequency 缸e chosen as representative bands of different 缸eas and considered to be the optimal bands used to build the regression model. Finally ,partial least squ缸es was used to build inversion mode l. The accuracy of this model was tested with cross-validated coefficient of determination (R;v) and cross 、 I validated root mean square error (RMSE凹) .The results show that the first derivative transformation can effectively improve the sensitivity of the original spectrum leaf nitrogen content inversion , and fully reflect the sensitivity of near infrared wave band representing leaf total nitrogen content. η】e accuracy of regression model based on the first derivative and the partial least-squares was much higher than that of the original spectra. In the regression model of the reed , verification accuracy (R;v) reached 0.84 , square root error (RMSEcv) was O. 11 , in the regression model of the cattail , verification accuracy (R;v) reached 0.66 , square root error (RMSEcv ) wω0.13 ， which were the optimal models to