Floating/emergent aquatic vegetation is an important aquatic vegetation group in lakes, and its area/coverage is an important parameter for lake ecological health assessment and carbon sequestration potential accounting. Accurately obtaining the area/coverage of floating/emergent aquatic vegetation over large lake areas and understanding their changes is crucial for lake ecological restoration and carbon sink accounting. Satellite remote sensing is the most effective means to obtain the area/cover of floating/emergent aquatic vegetation in lakes. However, traditional satellite monitoring methods can only obtain the presence or absence of aquatic vegetation within satellite pixels, and cannot quantitatively estimate the coverage of aquatic vegetation in the pixels Consequently, it is impossible to quantitatively and accurately obtain the area/coverage of floating/emergent aquatic vegetation in lakes. To address this issue, we utilized UAV, Sentinel-2 MSI, and Landsat 8 OLI remote sensing data. Using the XGBoost modeling method, we developed quantitative estimation models for floating and emergent aquatic vegetation coverage at the Sentinel-2 MSI and Landsat 8 OLI pixel scales through a stepwise upscaling approach, and successfully applied it to China’s four largest freshwater lakes. The results showed that the test sets of the two estimation models based on Sentinel and Landsat images had R₂ ^{of 0.95 and 0.97,} RMSE of 7.85% and 4.80%, and MAE of 5.35% and 3.35%, respectively. From 1990 to 2022, Lake Dongting and Lake Poyang showed highly significant increasing trends (p ＜ 0.01), Lake Taihu showed an increasing and then decreasing trend (p ＜ 0.01), and Lake Hongze had a non-significant increasing trend (p = 0.59). The long-term application of the model in the four largest freshwater lakes proved the robustness and application potential of the model, which is expected to provide methodological and data support for the accounting of carbon sinks in lake ecosystems and the assessment of carbon sequestration potential.