Anil Madhavapeddy

The paper finds that consistent crown phenology, not functional traits, is the key factor determining whether tropical tree species can be accurately mapped using imaging spectroscopy.

This paper evaluates geospatial foundation models for tree species mapping in mountain forests, finding they outperform traditional methods with fewer labels and preserve ecological structure, though performance degrades over time.

This study evaluates species-level canopy mapping in a hyperdiverse tropical forest using multi-temporal crown segmentation and airborne hyperspectral data, finding 70% canopy area correctly mapped to species.