Reliable subseasonal-to-seasonal-to-decadal (S2S2D) forecasts are essential for managing economic risk and informing planning in sectors such as energy, agriculture, water resources, and transportation. The use of artificial intelligence and machine learning (AI/ML) increasingly shows the potential to improve both S2S2D forecast skill and the computational time and cost. This session invites contributions that apply AI/ML methods and models to S2S2D timescale predictions of temperature and precipitation—especially where there is demonstrable operational potential or measurable gains in skill. We welcome work ranging from fully AI-driven models to the integration of ML tools with traditional modeling frameworks and components. This includes bias correction, process diagnostics, post-processing of ensemble output, and model explainability. Additionally, we encourage submissions that show how AI-driven innovations can strengthen model reliability, reduce costs, and support the delivery of actionable forecasts across public and private sectors.