Submerged aquatic vegetation (SAV) is crucial for maintaining a clear-water state in lakes. Tracking the spatiotemporal changes in SAV is crucial for understanding the ecological evolution, particularly in eutrophic lakes. Sentinel imagery offers high-resolution data for detailed SAV mapping. However, existing SAV classification algorithms based on Sentinel-2 multispectral instrument (MSI) require preprocessing to eliminate interference from other types such as floating-leaved aquatic vegetation and algal blooms (ABs), and also heavily rely on field survey data and human interventions, limiting the application for large-scale and long-term SAV monitoring. Here, we developed SSAVI-GMM, an algorithm leveraging a novel index, the Sentinel-based SAV index (SSAVI), derived from Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 MSI data, to automatically map SAV distribution using Gaussian mixture model (GMM) clustering. Testing in 19 lakes in the Yangtze Plain region yielded an average accuracy of 87.15%. This study marks a successful integration of SAR and optical data, addressing challenges in mapping SAV, and the robust GMM clustering method overcomes the limitations of traditional threshold methods. The SSAVI-GMM algorithm demonstrates promising potential for mapping SAV in shallow lakes globally.