The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and ra...The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. Hyperspectral reflectance （350 to 2500 nm） data were recorded at two different rice sites in two experiment fields with two cultivars, three nitrogen treatments and one plant density （45 plants m^-2）. Stepwise multivariable regression model （SMR） and RBF were used to compare their predictability for the leaf area index （LAI） and green leaf chlorophyll density （GLCD） of rice based on reflectance （R） and its three different transformations, the first derivative reflectance （D1）, the second derivative reflectance （D2） and the log-transformed reflectance （LOG）. GRNN based on D1 was the best model for the prediction of rice LAI and CLCD. The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed. Owing to its strong capacity for nonlinear mapping and good robustness, GRNN could maximize the sensitivity to chlorophyll content using D1. It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.展开更多
There is increasing interest in using hyperspectral data for quantitative characterization of vegetation in spatial and temporal scopes. Many spectral indices are being developed to improve vegetation sensitivity by m...There is increasing interest in using hyperspectral data for quantitative characterization of vegetation in spatial and temporal scopes. Many spectral indices are being developed to improve vegetation sensitivity by minimizing the background influence. The chlorophyll absorption continuum index (CACI) is such a measure to calculate the spectral continuum on which the analyses are based on the area of the troughs spanned by the spectral continuum. However, different values of CACI were obtained in this method because different positions of continuums were determined by different users. Furthermore, the sensitivity of CACI to agronomic parameters such as green leaf chlorophyll density (GLCD) has been reduced because the fixed positions of con- tinuums are determined when the red edge shifted with the change in GLCD. A modified chlorophyll absorption continuum index (MCACI) is presented in this article. The red edge inflection point (REIP) replaces the maximum reflectance point (MRP) in near-infrared (NIR) shoulder on the CACI continuum. This MCACI has been proved to increase the sensitivity and predictive power of GLCD.展开更多
基金Project supported by the National Natural Science Foundation of China (No.40571115)the National High Tech-nology Research and Development Program (863 Program) of China (Nos.2006AA120101 and 2007AA10Z205)
文摘The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. Hyperspectral reflectance （350 to 2500 nm） data were recorded at two different rice sites in two experiment fields with two cultivars, three nitrogen treatments and one plant density （45 plants m^-2）. Stepwise multivariable regression model （SMR） and RBF were used to compare their predictability for the leaf area index （LAI） and green leaf chlorophyll density （GLCD） of rice based on reflectance （R） and its three different transformations, the first derivative reflectance （D1）, the second derivative reflectance （D2） and the log-transformed reflectance （LOG）. GRNN based on D1 was the best model for the prediction of rice LAI and CLCD. The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed. Owing to its strong capacity for nonlinear mapping and good robustness, GRNN could maximize the sensitivity to chlorophyll content using D1. It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.
基金Project (Nos. 40571115 and 40271078) supported by the NationalNatural Science Foundation of China
文摘There is increasing interest in using hyperspectral data for quantitative characterization of vegetation in spatial and temporal scopes. Many spectral indices are being developed to improve vegetation sensitivity by minimizing the background influence. The chlorophyll absorption continuum index (CACI) is such a measure to calculate the spectral continuum on which the analyses are based on the area of the troughs spanned by the spectral continuum. However, different values of CACI were obtained in this method because different positions of continuums were determined by different users. Furthermore, the sensitivity of CACI to agronomic parameters such as green leaf chlorophyll density (GLCD) has been reduced because the fixed positions of con- tinuums are determined when the red edge shifted with the change in GLCD. A modified chlorophyll absorption continuum index (MCACI) is presented in this article. The red edge inflection point (REIP) replaces the maximum reflectance point (MRP) in near-infrared (NIR) shoulder on the CACI continuum. This MCACI has been proved to increase the sensitivity and predictive power of GLCD.
