Abstract
Leaf pigment content retrieval is an essential research field in remote sensing. However, retrieval studies on anthocyanins are quite rare compared to those on chlorophylls and carotenoids. Given the critical physiological significance of anthocyanins, this situation should be improved. In this study, using the reflectance, partial least squares regression (PLSR) and Gaussian process regression (GPR) were sought to retrieve the leaf anthocyanin content. To our knowledge, this is the first time that PLSR and GPR have been employed in such studies. The results showed that, based on the logarithmic transformation of the reflectance (log(1/R)) with 564 and 705 nm, the GPR model performed the best (R2/RMSE (nmol/cm2): 0.93/2.18 in the calibration, and 0.93/2.20 in the validation) of all the investigated methods. The PLSR model involved four wavelengths and achieved relatively low accuracy (R2/RMSE (nmol/cm2): 0.87/2.88 in calibration, and 0.88/2.89 in validation). GPR apparently outperformed PLSR. The reason was likely that the non-linear property made GPR more effective than the linear PLSR in characterizing the relationship for the absorbance vs. content of anthocyanins. For GPR, selected wavelengths around the green peak and red edge region (one from each) were promising to build simple and accurate two-wavelength models with R2 > 0.90.
Highlights
Anthocyanins exist widely in the plant kingdom, and accumulate in the vacuoles of cells and the tissues of plant vegetative and reproductive organs [1]
Gitelson and Solovchenko [17] compared the reflectance and absorbance (represented with –log(transmittance))-based approaches, and advised synergistic use to obtain accurate estimation. These studies have made great progress regarding the retrieval of the anthocyanin content, they are still rare in comparison to the fruitful retrieval studies on leaf chlorophylls and carotenoids
For anthocyanin reflectance index (ARI) and mARI, the results were more accurate (Table 7). These two vegetation indices performed better than the two final partial least squares regression (PLSR) models (Table 6); they were slightly worse than the two final Gaussian process regression (GPR) models (Table 4)
Summary
Anthocyanins exist widely in the plant kingdom, and accumulate in the vacuoles of cells and the tissues of plant vegetative and reproductive organs [1]. Gitelson and Solovchenko [17] compared the reflectance and absorbance (represented with –log(transmittance))-based approaches, and advised synergistic use to obtain accurate estimation These studies have made great progress regarding the retrieval of the anthocyanin content, they are still rare in comparison to the fruitful retrieval studies on leaf chlorophylls and carotenoids. Many advanced and sophisticated retrieval techniques have been proposed, such as stepwise multiple linear regression [18], partial least squares regression (PLSR) [19,20], continuous wavelet analysis [21], artificial neural network (ANN) [22], and Gaussian process regression (GPR) [23,24] These methods have not been reported to retrieve the leaf anthocyanin content yet. In this study, we explored two advanced techniques, i.e., PLSR and GPR, to retrieve the leaf anthocyanin content using spectral reflectance data. The TOTAL dataset was randomly evenly divided into 10 groups, and the threshold for the component significance was set at 0.952
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
