Remote sensing technology is the important tool of digital earth,it can facilitate nutrient management in sustainable cropping systems.In the study,two types of radial basis function(RBF)neural network approaches,the standard radial basis function(SRBF)neural networks and the modified type of RBF,generalized regression neural networks(GRNN),were investigated in estimating the nitrogen concentrations of oilseed rape canopy using vegetation indices(VIs)and hyperspectral reflectance.Comparison analyses were performed to the spectral variables and the approaches.The Root Mean Square Error(RMSE)and determination coefficients(R2)were used to assess their predictability of nitrogen concentrations.For all spectral variables(VIs and hyperspectral reflectance),the GRNN method produced more accurate estimates of nitrogen concentrations than did the SRBF method at all ranges of nitrogen concentrations,and the better agreements between the measured and the predicted nitrogen concentration were obtained with the GRNN method.This indicated that the GRNN method is prior to the SRBF method in estimation of nitrogen concentrations.Among the VIs,the Modified Chlorophyll Absorption in Reflectance Index(MCARI),MCARI1510,and Transformed Chlorophyll Absorption in Reflectance Index are better than the others in estimating oilseed rape canopy nitrogen concentrations.Compared to the results from VIs,the hyperspectral reflectance data also gave an acceptable estimation.The study showed that nitrogen concentrations of oilseed rape canopy could be monitored using remotely sensed data and the RBF method,especially the GRNN method,is a useful explorative tool for oilseed rape nitrogen concentration monitoring when applied on hyperspectral data.
Fumin WangJingfeng HuangYuan WangZhuanyu LiuDailiang PengFeifeng Cao
The oilseed rape growing in the lower reaches of Yangtze River in China belongs to winter varieties and suffers the risk of freezing injury.In this research,a typical freezing injury event occurred in Anhui Province was taken as a case study,the freezing damage degree of oilseed rape was assessed,and its development characteristics based on the vegetation metrics derived from MODIS and MERIS data were investigated.The oilseed rape was mapped according to the decline of greenness from bud stage to full-bloom period,with the phenological phases identified adopting time-series analyses.NDVI was more sensitive to freezing injury compared with other commonly used vegetation indices(VIs)calculated using MODIS bands,e.g.,EVI,GNDVI and SAVI.The freezing damage degree employing the difference between post-freeze growth and the baseline level in adjacent damage-free growing seasons was determined.The remote sensing-derived damage levels were supported by their correlation with the cold accumulated temperatures at the county level.The performance of several remote sensing indicators of plant biophysical and biochemical parameters was also investigated,i.e.,the photosynthetic rate,canopy water status,canopy chlorophyll content,leaf area index(LAI)and the red edge position(REP),in response to the advance of the freezing damage.It was found that the photosynthetic rate indicator—Photochemical Reflectance Index(PRI)responded strongly to freezing stress.Freezing injury caused canopy water loss,which could be detected though the magnitude was not very large.MERIS-LAI showed a slow and lagging response to low temperature and restored rapidly in the recovery phase;additionally,REP and the indicator of canopy chlorophyll content—MERIS Terrestrial Chlorophyll Index(MTCI),did not appear to be influenced by freezing injury.It was concluded that the physiological functions,canopy structure,and organic content metrics showed a descending order of vulnerabilities to freezing injury.