Proceedings Article | 18 November 2014
Proc. SPIE. 9298, International Symposium on Optoelectronic Technology and Application 2014: Imaging Spectroscopy; and Telescopes and Large Optics
KEYWORDS: Wavelet transforms, Statistical analysis, Data modeling, Spectroscopy, Wavelets, Remote sensing, Error analysis, Reflectivity, Photosynthesis, Radiative transfer
Chlorophyll plays an important role in crop photosynthesis, and it is an indicator of crop growth and stress state.
Estimation of leaf chlorophyll content of maize from remote sensing data was investigated using radiative transfer model
inversion and wavelet analysis. Hyperspectral data of maize were measured in two natural fields using ASD field
spectrometer, chlorophyll content was collected with a SPAD-502 chlorophyll meter. The bands between 350-1300nm
spectra region were selected for the preprocessing, 10 spectra of each sampling point measurements of maize were
averaged for smoothing. PROSPECT was used to generate very large spectral data sets, with which spectra region was set
to 350-1300nm. The original hyperspectral of maize were applied wavelet transform with wavelet function of Haar, DB9,
sym6, coif3, bior4.4, dmey to get transform coefficients, spectral reflectance of maize were obtained after the de-noising
processing. Support vector machine was trained the training data set, in order to establish hyperspectral estimation model
of chlorophyll content. A validation data set was established based on hyperspectral data, and the leaf chlorophyll content
estimation model was applied to the validation data set to estimate leaf chlorophyll content of maize. The hyperspectral
estimation model yielded results with a coefficient of determination of 0.8712 and a mean square error (MSE) of 76.1786.
The results indicated that by decomposing leaf spectra, the wavelet analysis can be used to a fast and accurate method for
estimations of chlorophyll content.