Remotely sensed water properties are important for a variety of applications, including validation of Earth Systems models (ESMs). However, the usefulness of operational forecasting products and directly-observing satellite-based sensors for validation of next-generation ESMs is limited due to their temporal availability and spatial resolution of < 1 year and > 10 km2 respectively. To address this validation data gap, we developed a data-driven model to produce high-resolution (< 1 km2) estimates of temperature, salinity, and turbidity over decadal time scales as required by next-generation ESMs. Our model fits daily MODIS Aqua reflectance data to surface observations (< 1 m depth) from 2000-2021 in Chesapeake Bay, USA. Our model has similar error statistics as prior efforts of this type for salinity (RMSE: 2.2) and temperature (RMSE: 1.9 C). However, unlike prior efforts our model is set up as a pipeline meaning that it has the advantage of producing predictions of water properties in future time periods as additional MODIS data is collected. In addition, our study is unique in that the predictions produced by our model are “geographically-aware” insofar as they capture geographic variation in the influence of flow and surface water exchange in upstream coastal watersheds.