Modelling and Mapping Forest Above-Ground Biomass Using Earth Observation Data

Accurate information on above-ground biomass (AGB) is important for sustainable forest management as well global initiatives aimed at combating climate change in the Tropics. In this study, AGB was estimated using a combination of field and Sentinel-2 earth observation data. The study conducted Magamba Nature Reserve Lushoto district, Tanzania. Field plot-based values were regressed against eighteen remote sensing variables (bands vegetation indices) Random Forest (RF) models based centroid weighted approaches. Results showed that model had highest fit precision (pseudo-R2 = 0.21, rRMSE 68.23%). A prediction map produced with mean 223.47 Mg ha-1 which close to (225.19 ha-1). Furthermore, standard deviation obtained from (i.e 174.04 ha-1) relatively lower compared one field-based measurements 97.42 This demonstrated imagery RF-based regression techniques have potential effectively support large scale estimation tropical rainforests.