Estimating standing biomass in papyrus (Cyperus papyrus L.) swamp: exploratory of in situ hyperspectral indices and random forest regression

Research demonstrates that narrow-band vegetation indices, particularly the Enhanced Vegetation Index (EVI), combined with random forest regression, can accurately estimate above-ground biomass (AGB) in dense papyrus swamps. The study identified optimal spectral bands—blue, red, red-edge, and near-infrared—as critical for biomass estimation, achieving high predictive accuracy (R² = 0.90; RMSEP = 0.289 kg/m²). This approach outperformed traditional NDVI-based methods, addressing a longstanding challenge in monitoring complex wetland ecosystems like the iSimangaliso Wetland Park and Maputo National Park. The findings highlight the potential of hyperspectral indices for precise biomass assessment in high-density vegetation, offering a robust tool for conservation and management.

Adam, E., Mutanga, O., Abdel-Rahman, E. M., & Ismail, R. (2014). Estimating standing biomass in papyrus (Cyperus papyrus L.) swamp: exploratory of in situ hyperspectral indices and random forest regression. International Journal of Remote Sensing, 35(2), 693–714. https://doi.org/10.1080/01431161.2013.870676