Linear models are often limited in capturing the complex, nonlinear behaviors of the climate system, leading to an increased interest in the application of Artificial Intelligence (AI) techniques within climate science. AI excels in identifying intricate linear and non-linear relationships within data, enhancing predictions, and deepening our understanding of climate processes from large-scale patterns to local weather events. This session will focus on how AI can advance our understanding of large-scale climate patterns to synoptic scale processes and their interactions as well as predictability, thereby improving weather forecasts, climate model development, climate impact assessments, and decision-making processes. We invite research that explores the predictability, classification, and characterization of climate patterns through AI methods. Contributions to hybrid approaches that combine AI with state-of-the-art climate models to better characterize and forecast large-scale to synoptic-scale climate patterns are also encouraged. Particularly, we seek submissions that demonstrate the added value of explainable AI over traditional methods in capturing the relationships between large-scale and synoptic-scale climate dynamics and their impacts on local weather events.