Sediments, nutrients, and pathogens are some of the most common sources of pollution that originate from various sources, including land and agricultural runoff, precipitation, and atmospheric deposition to name a few. Lakes Ontario, Erie, and smaller water bodies within their watersheds like the Finger Lakes are increasingly being impacted by nutrient, sediment loading, algal blooms, and pathogens due to climate changes (e.g., more frequent, and intense rainstorms) and accelerated agricultural and urban developments. This study developed a machine learning framework utilizing satellite and field data for generating wall-to-wall Secchi Disk Depth (one of water quality indicators) of 11 Finger lakes for the period of 2015-2024. The research focus on analyzing the spatiotemporal variations in water clarity across the 11 finger lakes, emphasizing seasonal and annual patterns. The results reveal notable patterns of water clarity changes, both seasonally and annually, showing clearer water in the spring and reduced clarity during summer to early fall. Additionally, a general trend of improving water clarity over the 2015–2024 period was observed in most lakes. While the method was developed, tested, and applied specifically to the Finger Lakes, it can be extended to other lakes in New York State and beyond, enabling water clarity backcasting as far as the availability of Landsat data allows (spanning several decades).