Forest fragmentation, caused by human activities, has negative consequences for forest health and biodiversity. The Sundarbans, situated in two densely populated countries, face ongoing human encroachment due to residential construction. This study investigated changes in forest cover and fragmentation in the Sundarbans, Bangladesh, from 2017 to 2023. The analysis used Sentinel-2 imagery and the Google Earth Engine (GEE) platform to classify water bodies, mangrove forests, built-up areas, and agriculture zones. Accuracy levels have not significantly fluctuated, but overall accuracy remained between 88 % and 91 %, with high agreement kappa statistics ranging from 0.83 to 0.88 across all years. The study identified Patch, Edge, Perforated, and Core forest classes, revealing annual shifts in land use. Notably, the ‘Patch’ class indicated localized regeneration, while the ‘Core (>202 ha)’ declined due to deforestation, urban expansion, and shifting agriculture. The Core class decreased significantly from 205,421 ha in 2017–73,127 ha in 2020. Additionally, Normalized Difference Vegetation Index (NDVI) indices highlighted fluctuations in forest classes and vegetation/non-vegetation areas. Canopy changes showed a 3 % reduction in high canopy (>0.3) from 2017 to 2023. High-resolution data facilitated the precise mapping of fragmented areas, emphasising the urgent need for conservation planning amidst urbanization while preserving the Sundarbans’ ecological integrity.