Training High-Resolution Weather Models (Regional) with NVIDIA Earth-2

NVIDIA Earth-2 is a platform for running GPU-accelerated weather and climate simulations at scale. This short tutorial explains how diffusion models enable new high-resolution weather applications and shows how you can train your own diffusion model for downscaling or forecasting with NVIDIA PhysicsNeMo. NVIDIA Earth-2 Portal: https://www.nvidia.com/en-us/high-performance-computing/earth-2/ GitHub (PhysicsNeMo): https://github.com/NVIDIA/physicsnemo/tree/main/examples/weather/stormcast Workshop recording (GTC 2026): https://www.nvidia.com/en-us/on-demand/session/gtc26-dlit81485/ Workshop materials (GTC 2026): https://github.com/openhackathons-org/End-to-End-AI-for-Science/tree/main/workspace/python/jupyter_notebook/GTC2026_HandsOnWithEarth-2