Machine learning is reshaping the representation of complex physical processes in Earth system models, offering new avenues for parameterization, emulation, and hybrid modeling. This session focuses on the use of machine learning to emulate computationally expensive or unresolved processes, accelerate physical simulations, enable data-driven discoveries, and improve representation across domains such as convection, turbulence, radiation, hydrology, sea ice, and other Earth system components. Topics include (but are not limited to):  

• Subgrid-scale parameterizations via machine learning  

• Emulators of physical processes, model components, or whole weather and climate models (including end-to-end learning and foundation models)  

• Data-driven discoveries  

• Hybrid ML-physics modeling frameworks  

• Physics-informed neural networks, neural operators, and differentiable programming  

• Reinforcement learning and other approaches for ensuring physical consistency, stability, and optimizing model behavior  

• Calibration and parameter optimization using ML  

• Verification and explainability (XAI) of data-driven models (including AI forecasting)  

• Coupling of ML models with physical models  

• Cross-domain applications (atmosphere, ocean, cryosphere, land). 

• A - Atmospheric Sciences
• C - Cryosphere
• IN - Informatics
• OS - Ocean Sciences