i-φ-MaLe: A novel hybrid machine learning phasor-based approach to retrieve a full-set of solar-induced fluorescence metrics and biophysical parameters

Solar-induced fluorescence (F) is crucial to monitor vegetation health, as it provides information about photosynthetic processes. Our new method, i-φ-MaLe, simultaneously estimates F spectra, Leaf Area Index (LAI), Chlorophyll Content (Cab), Absorbed Photosynthetic Active Radiation (APAR) and F Quantum Yield (Fqe) from canopy reflectance spectra by coupling the phasor approach with Machine Learning (ML) techniques. We validated i-φ-MaLe on simulations and spectra acquired for increasing spectrometer-canopy distances, up to 100 m (where O2 bands are affected by atmospheric oxygen absorption). The reliability of i-φMaLe in such complex experimental scenarios paves the way to new perspectives concerning the real time monitoring of vegetation stress status on high scales.