ChipsSeptember 16, 2026via NVIDIA Blog
University of Manchester Uses NVIDIA Earth-2 to Forecast Air Pollution Across the UK
Why it matters
A real-world deployment showing how AI compute platforms are replacing traditional scientific simulation — shifting the economics of environmental modeling and opening new use cases that were too expensive to run regularly.
Key signals
- NVIDIA Earth-2 platform deployed for air-quality forecasting
- Replaces traditional chemistry-based models (computationally expensive, limited detail/frequency)
- University of Manchester lead institution
- UK-wide air pollution prediction
- 30,000 estimated UK deaths per year from air pollution (impact context)
- Use case: data-driven insights replacing expensive traditional models
The hook
University of Manchester replaces expensive chemistry models with NVIDIA Earth-2, cutting air-pollution forecast compute costs while scaling detail across the UK.
Air pollution is a serious public health risk, contributing to an estimated 30,000 deaths in the U.K. alone last year. Data-driven insights can help — but computing air quality with traditional chemistry-based models is expensive, which limits how detailed they can be and how regularly they can be r…