Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices ...Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD, mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980’s. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used. Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.展开更多
A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning sys...A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning system) technology and change detection techniques at a 1:50000 mapping scale in the Letianxi Watershed of western Hubei Province, China. Satellite images (Landsat TM 1997 and Landsat ETM 2002) and thematic maps were used to provide comprehensive views of surface conditions such as vegetation cover and land use change. With ER Mapper and ERDAS software, the normalized difference vegetation index (NDVI) was computed and then classified into six vegetation density classes. ARC/INFO and ArcView software were used along with field observation data by GPS for analysis. Results obtained using spatial analysis methods showed that NDVI was a valuable first cut indicator for vegetation and land use systems. A regression analysis revealed that NDVI explained 94.5% of the variations for vegetation cover in the largest vegetation area, indicating that the relationship between vegetation and NDVI was not a simple linear process. Vegetation cover increased in four of areas. This meant 60.9% of land area had very slight to slight vegetation change, while 39.1% had moderate to severe vegetation change. Thus, the study area, in general, was exposed to a high risk of vegetation cover change.展开更多
Land surface process modeling of high and cold area with vegetation cover has not yielded satisfactory results in previous applications. In this study, land surface energy budget is simulated using a land surface mode...Land surface process modeling of high and cold area with vegetation cover has not yielded satisfactory results in previous applications. In this study, land surface energy budget is simulated using a land surface model for the A'rou meadow in the upper-reach area of the Heihe River Basin in the eastern Tibetan Plateau. The model performance is evaluated using the in-situ observations and remotely sensed data. Sensible and soil heat fluxes are overestimated while latent heat flux is underestimated when the default parameter setting is used. By analyzing physical and physiological processes and the sensitivities of key parameters, the inappropriate default setting of optimum growth and inhibition temperatures is identified as an important reason for the bias. The average daytime temperature during the period of fastest vegetation growth(June and July) is adopted as the optimum growth temperature, and the inhibition temperatures were adjusted using the same increment as the optimum temperature based on the temperature acclimation. These adjustments significantly reduced the biases in sensible, latent, and soil heat fluxes.展开更多
基金Project (Nos. 40571115 and 40271078) supported by the National Natural Science Foundation of China
文摘Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD, mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980’s. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used. Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.
基金Project Supported by the National Natural Science Foundation of China (No. 40271073).
文摘A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning system) technology and change detection techniques at a 1:50000 mapping scale in the Letianxi Watershed of western Hubei Province, China. Satellite images (Landsat TM 1997 and Landsat ETM 2002) and thematic maps were used to provide comprehensive views of surface conditions such as vegetation cover and land use change. With ER Mapper and ERDAS software, the normalized difference vegetation index (NDVI) was computed and then classified into six vegetation density classes. ARC/INFO and ArcView software were used along with field observation data by GPS for analysis. Results obtained using spatial analysis methods showed that NDVI was a valuable first cut indicator for vegetation and land use systems. A regression analysis revealed that NDVI explained 94.5% of the variations for vegetation cover in the largest vegetation area, indicating that the relationship between vegetation and NDVI was not a simple linear process. Vegetation cover increased in four of areas. This meant 60.9% of land area had very slight to slight vegetation change, while 39.1% had moderate to severe vegetation change. Thus, the study area, in general, was exposed to a high risk of vegetation cover change.
基金supported by the National Natural Science Foundation of China(Grant Nos.91125002,40971221)FP7 CEOP-AEGI(Coordinated Asia European Long-Term Observing System of the Qinhai Tibet Plateau Hydro-meteorological Processes and the Asian Monsoon System with Ground Satellite Image data and numerical simulation)project
文摘Land surface process modeling of high and cold area with vegetation cover has not yielded satisfactory results in previous applications. In this study, land surface energy budget is simulated using a land surface model for the A'rou meadow in the upper-reach area of the Heihe River Basin in the eastern Tibetan Plateau. The model performance is evaluated using the in-situ observations and remotely sensed data. Sensible and soil heat fluxes are overestimated while latent heat flux is underestimated when the default parameter setting is used. By analyzing physical and physiological processes and the sensitivities of key parameters, the inappropriate default setting of optimum growth and inhibition temperatures is identified as an important reason for the bias. The average daytime temperature during the period of fastest vegetation growth(June and July) is adopted as the optimum growth temperature, and the inhibition temperatures were adjusted using the same increment as the optimum temperature based on the temperature acclimation. These adjustments significantly reduced the biases in sensible, latent, and soil heat fluxes.
