Mangrove Species Mapping and Above-Ground Biomass Estimation in Suriname Based on Fused Sentinel-1 and Sentinel-2 Imagery and National Forest Inventory Data.

Obtaining state-of-the art data on the Mangrove cover extent is important to monitor possible responses to environmental changes such as land use change and mangrove ecosystem degradation caused by climate change. In this study, we examined the possibility of species-specific mapping within the mangrove area in Suriname based on the fusion of Sentinel-1 and Sentinel-2 data using the Google Earth Engine platform and a Random Forest classifier. To do this, a 2-level classification scheme was developed. In the first level, the mangrove cover was discriminated from mangrove graveyards and other land cover classes (kappa index of 80.65%). In the second level, the dominating mangrove species were successfully classified within the living mangrove cover (kappa index of 75.21 %). Secondly mangrove above-ground biomass (AGB) was estimated on a national scale, based on fused Sentinel-1 and Sentinel- 2 data and national mangrove forest inventory data by using a Support Vector Regression (SVR) machine learning technique, resulting in a root mean square error (RMSE) of 32.181 Mg.ha ⁻¹ and a R ² of 0.542.