Reservoir operations for saltwater intrusion mitigation in the tidal Susquehanna River

Reservoirs are critical infrastructure for the management of water resources, and reservoir operators must often balance multiple competing water demands. Climate change is an important threat to the resiliency of water resources in these reservoirs, as it can limit the efficacy of historical operations strategies as well as water demands and availability. The Conowingo Reservoir, a large multi-purpose reservoir located in Pennsylvania and Maryland along the Susquehanna River, has been managed actively for decades, yet current operating policies fail to adequately account for internal system variability and emerging threats to regional water resource reliability. Havre de Grace, Maryland, a small community at the mouth of the Susquehanna River, sources drinking water from the river, and duringperiods of low riverine freshwater flow, saline waters from Chesapeake Bay can migrate upstream, degrading public water supply and corroding infrastructure. To address this emerging problem, we combine a Conowingo Reservoir operations model with state-of-the-artreinforcement learning techniques to design optimal release policies that mitigate saltwater intrusion while continuing to meet existing competing water demands on the system. First, a predictive model for saltwater intrusion at the Havre de Grace drinking water intake is developed using historical data from 2007 – 2024. Salinity responses under low flow conditions are found to be highly non-linear and seasonal, highlighting the need for targeted reservoir releases prior to and during salinity events. Second, we will incorporate the predictive model into a simulation-optimization framework for the reservoir, training adaptive, state-aware, and dynamic release policies that release water from the reservoir downstream to flush out intruding saltwater. Updating the existing downstream releases to target saltwater intrusion events will protect downstream ecological health while providing finer control over rare nonlinear intrusion events that threaten public health and infrastructure.