Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method

Abstract

In order to estimate the chlorophyll content of maize plant non-destructively and rapidly, the research was conducted on maize at the heading stage using spectroscopy technology. The spectral reflectance of maize canopy was measured and processed following wavelet denoising and multivariate scatter correction (MSC) to reduce the noise influence. Firstly, the signal to noise ratio (SNR) and curve smoothness (CS) were used to evaluate the denoising effect of different wavelet functions and decomposition levels. As a result, the Sym6 wavelet basis function and the 5thlevel decomposition were determined to denoise the original signal. The MSC method was used to eliminate the scattering effect after denoising. Then three spectral ranges were extracted by interval partial least squares (IPLS) including the 525-549 nm, 675-749 nm and 850-874 nm. Finally, the chlorophyll content estimation model was developed by using support vector regression (SVR) method. The calibration Rc2of the SVR model was 0.831, the RMSEC was 1.3852 mg/L; the validation Rv2was 0.809, the RMSEP was 0.8664 mg/L. The results show that the SNR and CS indicators can be used to select the parameters for wavelet denoising and model can be used to estimate the chlorophyll content of maize canopy in the field.