Manchester uses NVIDIA Earth-2 to forecast UK air pollution

The University of Manchester worked with NVIDIA to train Earth-2 generative downscaling models on the UK supercomputer Isambard-AI to forecast nationwide air pollution, producing time-dependent pollution fields without expensive chemistry-based models. The work shows Earth-2 CorrDiff and StormCast can generate scenarios for policy-relevant air quality forecasting and observational assimilation.

• Nvidia partner GMI Cloud seeks $300M loan for chips2026-09-17
• NVIDIA advances native GPU programming in Rust2026-09-17
• Huawei to unveil China’s answer to Nvidia AI chips2026-09-17
• Nvidia: robots await a ChatGPT moment2026-09-16
• NVIDIA Vera Rubin NVL72 tops MLPerf Inference v6.12026-09-16