The societal impacts of climate variability and extreme events are increasingly pronounced, demanding transformative approaches to prediction and decision-making. Rapid advances in artificial intelligence (AI) and machine learning (ML), including deep learning, generative AI, and hybrid physics-informed methods, are reshaping climate science and its applications.

This session invites contributions leveraging AI/ML to advance understanding and prediction of climate variability across scales, including phenomena such as the El Niño-Southern Oscillation and the Indian Ocean Dipole, as well as compound and high-impact extremes. We encourage studies integrating data-driven and dynamical approaches, including AI-enhanced model initialization, parameterization, emulation, and high-resolution downscaling.

Beyond core climate applications, the session highlights cross-sectoral impacts, particularly climate-informed health risk prediction (e.g., malaria, dengue), early warning systems, and decision-ready climate services. Contributions on uncertainty quantification, explainability, trustworthy AI, and integration of satellite, in situ, and socio-economic data are especially welcome.

• GH - GeoHealth
• H - Hydrology
• NH - Natural Hazards
• OS - Ocean Sciences