Wetlands are vital in the sustainability of ecosystems by performing functions such as cleaning of polluted waters, providing habitat for flora and fauna, assisting with downstream flood peaks, and recharging groundwater aquifers which warrant the need for the protection and restoration of degraded wetlands. The Wetland Reserve Program (WRP) by the Natural Resources Conservation Service (NRCS) evaluates the performance of restoration practices implemented on the easements in West Tennessee and Kentucky enrolled in the program. This study aims to provide baseline hydrological parameters such as water depth and hydroperiod before the restoration period which can be used in a comparative analysis to ascertain wetland enhancements. Cloud-based computing platforms such as Google Earth Engine (GEE) provides open-access satellite data streams and computing resources for environmental monitoring and mapping. The study intends to utilize the GEE platform to analyze time series of historical Landsat, Sentinel-1, and Sentinel-2 satellite images to detect and classify surface water in the wetlands to construct a time series of the dynamics of surface water. Machine learning algorithms will be employed to fill in the gaps between satellite revisit times using precipitation and temperature parameters as input. This will enable us to generate a continuous dataset for statistical analysis as against the current water level monitoring being undertaken by the WRP using HOBO MX2001 water level loggers.