Advances in in-situ sensor networks, Internet of Things (IoT) frameworks, and process-guided modeling are essential for providing accurate short- to medium-term forecasts of key water quality parameters, including nitrates, dissolved oxygen, and salinity. Sensor technologies and process-based and machine learning computational tools have expanded our predictive capabilities. However, significant gaps remain in developing scalable methods for small and ungaged catchments that are acutely sensitive to minor environmental shifts. In mixed urban-rural landscapes, integrating complex computational models to pinpoint contamination sources is a vital pathway toward mitigating human impacts. In this session, we invite submissions that explore the synergy between hydrological forecasting, pollutant transport modeling, and real-time monitoring systems to illuminate our understanding of landscape responses across various timeframes. We particularly encourage research focused on small, mixed-use watersheds that demonstrate innovative strategies for the observation and forecasting of aquatic ecosystem health and human impacts.

• B - Biogeosciences
• GC - Global Environmental Change
• IN - Informatics