Machine learning (ML) has expanded the toolkit of watershed science, offering speed and flexibility for analyzing complex systems. Yet, data scarcity and high-dimensional, non-linear dynamics often constrain its utility. Consequently, the field is shifting toward Hybrid Modeling—integrating mechanistic physics with ML to ensure physical consistency across diverse hydrologic regimes. This evolution extends to research workflows, where LLM-assisted development and Markdown-based documentation are accelerating the cycle from hypothesis to discovery. We welcome submissions spanning traditional ML, physics-based modeling, and Agentic AI. We are particularly interested in: (a) Traditional and Physics-informed ML, (b) Agentic AI and autonomous reasoning, (c) Explainable AI (XAI), (d) Generative AI for data augmentation, (e) Transfer learning, and (f) AI-assisted tools to streamline and scale Earth system modeling.

• B - Biogeosciences
• GC - Global Environmental Change
• NG - Nonlinear Geophysics