Natural wetlands intrinsically heterogeneous, and are typically composed of a mosaic of ecosystem patches with different plant types. The adaptation of these plants communities to water-dominated environment is the basis for their use in improving the water quality in constructed wetlands. The understanding of wetland vegetation effects on the environment is the key to determine which plant to grow in a constructed wetland in term of nutrients removal. Wetland vegetation can influence water movement. The plant density and life form affect the drag and thus controls the residence time of water in different parts of the wetlands, as well as the rate of deposition of suspended solids. Furthermore, emergent plants with high transpiration rates can lower the water level. Accurately identifying the vegetation patches is important to understanding their hydrological effects and further effects on nutrients removal. Compared to labor consuming field survey, remote sensing is an efficient way to monitor plant communities in wetlands. However, wetlands are typically small and vegetation patches within wetland vary at an even smaller scale, such that moderate resolution will not be able to discern the different vegetation. Alternatively, the NASA’s Harmonized Landsat Sentinel-2 (HLS) makes it possible to acquire moderate-high spatial resolution imagery at high temporal resolution, which creates the opportunity to build time series of wetland vegetation characteristics at sufficient spatial and temporal resolutions. This study aims to use NDVI time series generated from NASA’s HLS dataset to classify vegetation patches at an estuarine wetland. We collected HLS data for the year of 2019 and generated the NDVI time series for each pixel of the wetland. Unsupervised classification was then applied on these pixels using the time series. And results will be evaluated with ground truth points.