Exploring spectral and phylogenetic diversity links with functional structure of aquatic plant communities

As freshwater ecosystems are threatened globally, the conservation of aquatic plant diversity is becoming a priority. In the last decade, remote sensing has opened up new opportunities to measure biodiversity, especially across terrestrial biomes, and the combination of spectral features with additional information derived from community phylogeny can further advance the accurate characterisation of plant functional diversity across scales. In this study, we explored the use of spectral features extracted from centimetre resolution hyperspectral imagery collected by a drone and phylogenetic metrics derived from a fully resolved supertree to estimate functional diversity (richness, divergence, and evenness) using non-linear parametric and machine learning models within communities of floating hydrophytes and helophytes sampled from different sites. Our results show that all three functional diversity metrics can be estimated from spectral features using machine learning models (random forest; R 2 = 0.90–0.92), while parametric models perform worse (generalised additive models; R 2 = 0.40–0.79), especially for community evenness. Merging phylogenetic and spectral features improves modelling performance for functional richness and divergence (R 2 = 0.95–0.96) using machine learning, but only significantly benefits community evenness estimation when parametric models are used. The combination of imaging spectroscopy and phylogenetic analysis can provide a quantitative way to capture variability in plant communities across scales and gradients, to the benefit of ecologists focused on the study and monitoring of biodiversity and related processes. • Spectral-phylogenetic-functional diversity links newly explored in wetlands. • Spectral metrics effectively surrogate functional diversity of aquatic plants. • Machine learning regression outperforms non-linear parametric models. • Merging spectral and phylogenetic features improves functional structure prediction.