Many hydrologic systems are strongly influenced by infrastructure and operational decisions, yet most machine learning (ML) and deep learning (DL) applications focus on natural systems. This session focuses on hybrid approaches that integrate ML and DL with existing modeling frameworks, operations models, and decision support tools for managed water systems, including reservoirs, diversions, and regulated river basins.

We welcome contributions on:

• Integration of ML/DL with reservoir operations models and decision support tools
• Hybrid modeling approaches that combine process-based models with data-driven methods
• Representation and emulation of operational rules and infrastructure in machine learning and deep learning frameworks
• Use of data-driven methods to improve system monitoring, forecasting, and decision-making
• Evaluation of hybrid models in managed and regulated water systems
• Uncertainty quantification in ML and DL prediction for managed water systems

This session highlights how ML/DL can enhance existing modeling and operational frameworks to improve understanding, prediction, and management of water systems.