Assessing canopy nitrogen and carbon content in maize by canopy spectral reflectance and uninformative variable elimination

Assessing canopy nitrogen content(CNC) and canopy carbon content(CCC) of maize by hyperspectral remote sensing data permits estimating cropland productivity, protecting farmland ecology, and investigating the nitrogen and carbon cycles in the atmosphere. This study aimed to assess maize CNC and CCC using canopy hyperspectral information and uninformative variable elimination(UVE). Vegetation indices(VIs) and wavelet functions were adopted for estimating CNC and CCC under varying water and nitrogen regimes. Linear, nonlinear, and partial least squares(PLS) regression models were fitted to VIs and wavelet functions to estimate CNC and CCC, and were evaluated for their prediction accuracy.UVE was used to eliminate uninformative variables, improve the prediction accuracy of the models, and simplify the PLS regression models(UVE-PLS). For estimating CNC and CCC, the normalized difference vegetation index(NDVI, based on red edge and NIR wavebands) yielded the highest correlation coefficients(r > 0.88). PLS regression models showed the lowest root mean square error(RMSE) among all models. However, PLS regression models required nine VIs and four wavelet functions, increasing their complexity. UVE was used to retain valid spectral parameters and optimize the PLS regression models.UVE-PLS regression models improved validation accuracy and resulted in more accurate CNC and CCC than the PLS regression models. Thus, canopy spectral reflectance integrated with UVE-PLS can accurately reflect maize leaf nitrogen and carbon status.

Predicting Nitrogen Status of Rice Using Multispectral Data at Canopy Scale

Two field experiments were conducted in Jiashan and Yuhang towns of Zhejiang Province, China, to study the feasibility of predicting N status of rice using canopy spectral reflectance. The canopy spectral reflectance of rice grown with different levels of N inputs was determined at several important growth stages. Statistical analyses showed that as a result of the different levels of N supply, there were significant differences in the N concentrations of canopy leaves at different growth stages. Since spectral reflectance measurements showed that the N status of rice was related to reflectance in the visible and NIR (near-infrared) ranges, observations for rice in 1 nm bandwidths were then converted to bandwidths in the visible and NIR spectral regions with IKONOS (space imaging) bandwidths and vegetation indices being used to predict the N status of rice. The results indicated that canopy reflectance measurements converted to ratio vegetation index (RVI) and normalized difference vegetation index (NDVI) for simulated IKONOS bands provided a better prediction of rice N status than the reflectance measurements in the simulated IKONOS bands themselves. The precision of the developed regression models using RVI and NDVI proved to be very high with R2 ranging from 0.82 to 0.94, and when validated with experimental data from a different site, the results were satisfactory with R2 ranging from 0.55 to 0.70. Thus, the results showed that theoretically it should be possible to monitor N status using remotely sensed data.

A novel wavelength selection strategy for chlorophyll prediction by MWPLS and GA

The research proposed a novel wavelength selection strategy by the combination of moving window partial least squares(MWPLS)and genetic algorithm(GA)for the chlorophyll content detection of winter wheat canopy using spectroscopy technology.Firstly,the original spectral dataset was pre-processed by wavelet denosing,multiple scatter correction.Then,abnormal data samples were removed by Pauta Criterion and the dataset was divided into modeling set and validation set by SPXY.Finally,the sensitive wavebands were selected using MWPLS method and MWPLS+GA respectively and partial least squares(PLS)models were established for chlorophyll content prediction.For the model established by using all the wavebands in the region of 400-900 nm,its R_(c)^(2) and R_(v)^(2) were 0.4468 and 0.3821 respectively;its modeling root mean square error(RMSEM)and verification root mean square error(RMSEV)were 2.9057 and 1.7589 respectively.For the model established by using 151 wavebands selected by MWPLS,its R_(c)^(2) and R_(v)^(2) were 0.6210 and 0.5901 respectively;its RMSEM and RMSEV were 2.4007 and 1.6408 respectively.For the model established by using 36 wavebands selected by MWPLS+GA,its R_(c)^(2) and R_(v)^(2) were 0.7805 and 0.7497 respectively;its RMSEM and RMSEV were 1.8504 and 1.1315 respectively.The results show that wavelength selection can remove redundant information and improve model performance.The strategy of combining MWPLS with GA has also been proved to work well in selecting sensitive wavebands for chlorophyll content prediction.