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
Combined with remote sensing data and meteorological data, cold damage risk was assessed for planting area of double cropping rice （DCR） in Hunan Province, China. A new methodology of cold damage risk assessment was...Combined with remote sensing data and meteorological data, cold damage risk was assessed for planting area of double cropping rice （DCR） in Hunan Province, China. A new methodology of cold damage risk assessment was built that apply to grid and have clear hazard-affected body. Each station cold damage annual frequency and average annual intensity of cold damage was calculated by using 1951-2010 station daily mean temperature and simple cold damage identification index. On this basis, average annual cold damage risk index was obtained by their product. The spatial analysis models of cold damage risk index about double-season early rice （DSER） and double-season later rice （DSLR） were established respectively by the relation of average annual cold damage risk index and its geographic factors. Critical threshold of level of average annual cold damage risk index for DSER and DSLR were respectively divided by the correlative equation of cold damage annual frequency and average annual intensity of cold damage. 2001-2010 planting area of DCR, acquired by time series analysis of MOD09AI 8-d composite land surface reflectance product, was as target of assessment. The results show average annual intensity of cold damage is exponential function of cold damage annual frequency, average annual cold damage risk index is directly proportional to cold damage cumulant and cold damage annual frequency, and is inversely proportional to happen times of cold damage and the square of statistical time sequence length. Cold damage risk of DSER is higher than DSLR in Hunan Province. In the 10-yr stacking map, DCR planting in low risk area accounted for 11.92% of total extraction area, in moderate risk area accounted for 69.62%, in high risk area accounted for 18.46%. According to the cold damage risk assessment result, DCR production can be guided to reduce cold damage losses.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funded by the Key Technologies R&D Program of China during the 12th Five-Year Plan period(2011BAD32B01)the National Natural Science Foundation of China(40875070)the Research Fund for Doctoral Program of Higher Education,China(20100101110035)
文摘Combined with remote sensing data and meteorological data, cold damage risk was assessed for planting area of double cropping rice （DCR） in Hunan Province, China. A new methodology of cold damage risk assessment was built that apply to grid and have clear hazard-affected body. Each station cold damage annual frequency and average annual intensity of cold damage was calculated by using 1951-2010 station daily mean temperature and simple cold damage identification index. On this basis, average annual cold damage risk index was obtained by their product. The spatial analysis models of cold damage risk index about double-season early rice （DSER） and double-season later rice （DSLR） were established respectively by the relation of average annual cold damage risk index and its geographic factors. Critical threshold of level of average annual cold damage risk index for DSER and DSLR were respectively divided by the correlative equation of cold damage annual frequency and average annual intensity of cold damage. 2001-2010 planting area of DCR, acquired by time series analysis of MOD09AI 8-d composite land surface reflectance product, was as target of assessment. The results show average annual intensity of cold damage is exponential function of cold damage annual frequency, average annual cold damage risk index is directly proportional to cold damage cumulant and cold damage annual frequency, and is inversely proportional to happen times of cold damage and the square of statistical time sequence length. Cold damage risk of DSER is higher than DSLR in Hunan Province. In the 10-yr stacking map, DCR planting in low risk area accounted for 11.92% of total extraction area, in moderate risk area accounted for 69.62%, in high risk area accounted for 18.46%. According to the cold damage risk assessment result, DCR production can be guided to reduce cold damage losses.
