GSV-L: A general spectral vector model for hyperspectral leaf spectra simulation

Abstract

Leaf optical spectra determine vegetation canopy optical spectra. Physically based leaf models are relatively complicated as they require many biophysical and biochemical parameters that are usually difficult to obtain. The aim of this study is to develop a new empirical model, the general spectral vector-leaf (GSV-L) model using globally collected leaf spectra data. A global field-measured leaf spectra database, including 66,478 leaf reflectance and 3575 transmittance spectra in the wavelength range of 400–2400 nm, was first constructed. The singular value decomposition (SVD) method was applied to the field data matrix to derive the spectral vectors for leaf spectral modeling. The SVD method was also compared with the successive approximation (SA) and principal component analysis (PCA) methods using the same training and validation datasets, and the GSV-L model was compared with two other physical models, PROSPECT and LEAF-SIP. The GSV-L model can be used to simulate full leaf reflectance and transmittance spectra using a few wavelengths in different bands with very high R2 (0.99, 0.99), small RMSE (0.014, 0.014) and bias (0, 0.002) values. The model also performs better than the PROSPECT and LEAF-SIP models for leaf spectral simulation. The coefficients of the reflectance spectral vectors can be used to estimate leaf structure parameters, equivalent water thickness, and leaf biochemical contents. As an efficient and accurate approach for leaf hyperspectral modeling, GSV-L can also be integrated with various canopy reflectance and land surface models.