Novel spectral indices for enhanced estimations of 3-dimentional flavonoid contents for Ginkgo plantations using UAV-borne LiDAR and hyperspectral data

Abstract

Leaf flavonoid content (LFC) is a marked indicator of the protection signals from biotic and abiotic stresses, as well as the potential in the recovery of phenolic compounds from plants for producing potent antioxidants. LFC has been non-destructively retrieved from leaf reflectance spectra in recent studies. However, the LFC estimation from canopy-level spectra remains poorly understood and challenging arise from the confounding effects of other pigments and canopy structure. To address this limitation, this study proposed a suite of new 3-Dimentional spectral indices (SIs), in which the leaf-level standard flavonoid indices (FIs) are normalized by structure indices or chlorophyll indices. The hypothesis investigated is that these new SIs, derived from UAV-based hyperspectral point cloud data (fused by canopy hyperspectral images and LiDAR point cloud data), can enhance detecting LFC distribution within the canopies of Ginkgo plantations, by mitigating the effects of canopy structure and chlorophyll absorption. The results demonstrated that most chlorophyll-based normalized indices (CV-R2 = 0.56–0.65) outperformed the structure-based normalized indices (CV-R2 = 0.44–0.57) and the standard FIs (CV-R2 = 0.19–0.54). In specific, FI420,710/SR800,710 (CV-R2 = 0.65) out of chlorophyll-based normalized indices performed better than other indices. With the use of FI420,710/SR800,710, the 3-Dimentional distribution of LFC within Ginkgo canopies can be well mapped. In summary, this study indicates marked potentials of the developed normalized indices for mapping LFC distribution, as well as providing new insight into alleviating the confounding effects of chlorophyll and structure on LFC estimation of Ginkgo plantations, with simulations conducted by the canopy radiative transfer model.