As a unique wetland type, forest swamps play an important role in regional carbon cycling and biodiversity conservation. Taking Hani wetland in Jilin province as the research object, we integrated the application of Sentinel-1 radar and Sentinel-2 multispectral images, fully exploited the potential of Sentinel-1 multi-polarization band features and Sentinel-2 red edge index for forest swamp remote sensing identification, and applied the random forest method to realize the extraction of forest swamp distribution information of Hani wetland. The results show that when the optimal number of decision trees for forest swamp information extraction is 1200, the fusion of Sentinel-1VV and VH backscattering coefficient radar band features and Sentinel-2 red-edge band features can significantly improve the extraction accuracy of forest swamp distribution information, and the overall accuracy and Kappa coefficient of forest swamp information extraction in protected areas are as high as 89% and 0.85, respectively. The overall accuracy and Kappa coefficient of forest swamp information extraction in the protected area were 89% and 0.85, respectively. The landscape types of Hani Wetlands of International Importance are diversified, with natural wetlands, artificial wetlands and non-wetland landscape types co-existing. Among the natural wetland types, the forest swamp has the largest area of 27.1 km2, accounting for 11.2% of the total area of the reserve; the river has the smallest area of 0.7 km2, accounting for 0.3% of the total area of the reserve. The forest swamp extraction method provides data support for the sustainable management of Hani wetlands and case guidance for forest swamp mapping in other regions.