Improving the Estimation of Apple Leaf Photosynthetic Pigment Content Using Fractional Derivatives and Machine Learning

As a key functional trait, leaf photosynthetic pigment content (LPPC) plays an important role in the health status monitoring and yield estimation of apples. Hyperspectral features including vegetation indices (VIs) derivatives are widely used retrieving biophysical parameters. The fractional derivative spectral method shows great potential LPPC. However, performance machine learning (ML) for apple LPPC still needs to be explored. objective this study is test capacity using ML methods retrieve Here, hyperspectral data 400–2500 nm domains was calculate order 0.2–2, then sensitive bands were screened through feature dimensionality reduction train build model. Additionally, VIs-based empirical regression models developed compare with methods. results showed that derivative-driven have higher accuracy than driven by original spectra or index. also perform better models. Specifically, best estimates chlorophyll carotenoid achieved support vector (SVR) at 0.2 (R2 = 0.78) 0.4 0.75), respectively. maintained good universality multiple phenological periods. Therefore, highlights improved