Skip to content
Neural Daily

ModelsNews

NVIDIA StormScope EU: short-range weather AI for Europe

NVIDIA's Earth-2 open model family adds StormScope EU, trained on European data, which forecasts cloud conditions from Meteosat imagery at 10-minute intervals.

By: Mikola Máté Patrik · · 2 min read

NVIDIA Earth-2 collage: AXA cyclone seasons, historical versus AI ensemble, a Vaisala globe forecast and an Earthmover satellite cloud map of Europe
Image: NVIDIA · Press kit · Official NVIDIA blog social image (og:image) · Source

What changed?

At GTC Berlin, NVIDIA announced (NVIDIA blog) that StormScope EU has joined its Earth-2 family of open weather and climate models. It is a regional version of the StormScope short-range forecasting model, trained on European weather and climate data.

The model uses EUMETSAT satellite observations to predict evolving cloud conditions across 16 Meteosat channels at 10-minute intervals. A live demo built with Earthmover runs at the conference: Earth2Studio produces the forecasts, and the results are served as map tiles, so visitors can explore any part of Europe without downloading the full dataset.

What you can build

  • StormScope handles short-term forecasting, while CorrDiff adds local detail to coarser weather data. The two can be chained in one workflow.
  • The model architectures can be retrained for other environmental tasks such as air-quality modeling. The open source PhysicsNeMo framework provides the training and customization tools.
  • University of Manchester researchers adapted CorrDiff for U.K. air-quality modeling, training it on the Isambard-AI supercomputer and running it locally on DGX Spark systems.

Who is using it

AXA uses FourCastNet 3 to study regional cyclone risk across more than 1,000 simulated seasons, far beyond the historical record. Vaisala Xweather is adapting StormScope with lightning data to extend warning lead time. TotalEnergies is evaluating StormScope-based solar-radiation nowcasts at two photovoltaic sites.

Why it matters

Global models show where a storm is forming, but decisions about a solar farm, a shipping route or an insured portfolio depend on local, sub-hourly data. StormScope EU targets that gap, and as an open model it can be fine-tuned on your own data. If you work on energy, logistics or insurance products, the Earth2Studio examples are a good starting point. NVIDIA did not publish accuracy figures in the announcement.

    Produced with the help of AI, reviewed by an editor. How we make our articles

    Reviewed and edited by the Neural Daily desk. About

    Related articles