Mangroves are an important ecosystem that stores massive amounts of carbon in above-ground biomass (AGB). However, climate change is greatly impacting the growth and distribution of mangroves. AGB monitoring is critical for gaining a thorough understanding of carbon sequestration and the overall health of mangrove ecosystems. In this study, we used high-resolution satellite imagery from Landsat 8 and Sentinel-2 data, to obtain the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Normalized Difference Water Index (NDWI), which are commonly used for evaluating the vegetation density and health. By projecting future environmental conditions affecting mangrove growth and biomass were examined by climate models (CMIP6). In order to increase the accuracy of AGB predictions under climate change scenarios, the random forests and support vector machine learning algorithms have used to combine climate projections with data from remote sensing. Temporal analysis performed to evaluate how climate-induced factors, such as rising sea levels, increased temperatures, and extreme weather patterns, influence AGB dynamics over time. The findings show that substantial differences in AGB estimations can result from climate change, especially because of the increased frequency of extreme weather events and altered environmental factors. The research offers a thorough method for evaluating how vulnerable mangrove ecosystems are to climate change, providing insightful information for Guangdong Province policymakers and conservationists.
 

above-ground biomass (AGB), remote sensing, NDVI, coastal region, China, biomass estimation, machine learning, vegetation indices