Artificial intelligence (AI) is transforming how we monitor, understand, predict, and manage water quality across rivers, lakes, reservoirs, estuaries, and coastal systems. Recent advances in machine learning, deep learning, and hybrid process-informed AI show strong potential for capturing complex spatiotemporal dynamics of nutrients, sediment, dissolved oxygen, temperature, harmful algal blooms, etc. As these tools move toward real-world application, key questions remain: What challenges arise in operational deployment? How can AI advance scientific understanding of hydrological, biogeochemical, and human influences on water quality? What are the next frontiers? This session invites critical reflections and practical insights into what works, what doesn’t, and why. We welcome contributions from hydrologists, environmental scientists, and AI researchers on topics including: model training and operational deployment, integrating domain knowledge into AI, quantifying model trustworthiness, and AI-driven scientific discovery. We especially encourage work on foundation models and multimodal models integrating sensor, remote sensing, text, and image data.