Accurate prediction of precipitation across time scales—from short-term to subseasonal-to-seasonal, interannual, and decadal—is essential for advancing our understanding of the water cycle and supporting sustainable water resource management. Reliable spatiotemporal information on precipitation and its underlying mechanisms can benefit critical sectors such as energy, transportation, agriculture, and disaster preparedness. Artificial intelligence (AI)–based precipitation prediction is rapidly emerging alongside traditional numerical weather and climate models, offering new opportunities for innovation.

This session highlights interdisciplinary research that integrates physical modeling and AI to enhance our understanding of precipitation and broaden its applications. We invite submissions on, but are not limited to: AI-based and physical model–based precipitation prediction and analysis; hybrid AI-physics modeling and data assimilation approaches; the use of diverse observations and AI to assess precipitation predictability; the challenges and opportunities of precipitation prediction in the AI era. Contributions from atmospheric, hydrological, and data/AI sciences are especially encouraged.

• GC - Global Environmental Change
• H - Hydrology
• NH - Natural Hazards