Guozhen AIGlobal AI field notes and model intelligence

Realtime AI News

NVIDIA's Earth-2 lands in Europe with StormScope EU, a 10-minute regional forecast model

NVIDIA said European organizations are putting Earth-2 open models into operational weather work and introduced StormScope EU, a regional nowcasting model that predicts cloud conditions across 16 Meteosat channels every 10 minutes using EUMETSAT observations. AXA, Vaisala Xweather, University of Manchester and TotalEnergies are already building on it.

Published
英伟达 Earth-2 在欧洲落地:新模型 StormScope EU 每 10 分钟更新一次预报
Image source: blogs.nvidia.com

NVIDIA said organizations across Europe are putting its Earth-2 family of open weather and climate models into operational work, from reinsurance hurricane risk to short-term solar forecasting.

The newest addition is StormScope EU, a regional version of the StormScope short-term forecasting model trained on European weather and climate data. It uses EUMETSAT satellite observations to predict evolving cloud conditions across 16 Meteosat channels at 10-minute intervals.

At GTC Berlin, NVIDIA is showing a live pipeline built with Earthmover: Earth2Studio runs the forecasts, Earthmover's data platform manages and serves real-time results that refresh as new satellite observations arrive every 10 minutes, and the output is delivered as map tiles so visitors can explore predictions without downloading whole datasets.

Developers can combine the models in their own workflows, using StormScope for nowcasting and CorrDiff to add local detail to coarser global data, and can retrain the architectures for other environmental applications such as air quality. The open-source PhysicsNeMo framework supplies training and customization tooling so teams can fold in proprietary data and domain expertise.

Among the named users, AXA is applying Earth-2's FourCastNet 3 to regional cyclone risk beyond the historical record, running more than 1,000 simulated seasons to inform risk assessments and help customers target prevention.

Vaisala Xweather is combining Earth-2 with its own observations, lightning data and forecasting expertise, adapting StormScope with lightning data to extend short-term lead time and pushing those warnings into its software-as-a-service products and AI assistant integrations.

University of Manchester researchers adapted CorrDiff for UK air-quality modeling, training on the NVIDIA-powered Isambard-AI supercomputer and running it locally on DGX Spark systems, moving environmental modeling from a national supercomputer to a desk. TotalEnergies is evaluating StormScope-based solar-radiation nowcasts at two photovoltaic sites, working toward sub-hourly weather information.

The pitch is not one best-in-class weather model but a modular family plus tooling for simulation and deployment. What decides whether it works is whether local operators can tune these models to operational accuracy with their own observations, which is exactly what the AXA, Vaisala and Manchester cases are meant to demonstrate.

Why it matters

A modular open model family plus simulation and deployment tooling moves weather AI from demos to localized operations, with energy, insurance and transport as the first paying users.

NVIDIAWeather AIOpen Models
Back to realtime news

Nearby Updates

All

10/22, 13:00

NVIDIA pitches open models to European retail: 90% cheaper serving at Shopify, warehouses simulated first

NVIDIA detailed European retail deployments built on its open models and accelerated computing, including Shopify post-training Nemotron 3.5 Lightning for a Sidekick subagent to cut serving costs 90 percent while answering seven times faster. Otto Group, Zooplus, Photoroom and L'Oréal also appear, with warehouse operations tested in Omniverse simulation before physical rollout.

10/22, 13:00

NVIDIA widens DSX platform as GE Vernova, Hitachi Energy and Schneider Electric plug in

NVIDIA detailed how energy and electrical equipment makers are building on its DSX AI Factory Platform, with GE Vernova, Hitachi Energy, Schneider Electric and Siemens Energy contributing grid simulation, storage certification and Vera Rubin power and cooling reference designs. NVIDIA says power is now infrastructure's biggest bottleneck, with more than $300 billion of equipment backlogged and over 200 gigawatts of projects waiting in U.S. interconnection queues.

10/22, 13:00

NVIDIA Cosmos adds training, evaluation and deployment tools plus Data Factory blueprints

NVIDIA has expanded Cosmos with new training tools, simulation checkpoints and Cosmos Data Factory blueprints for building world models faster. The company says Cosmos ranks top five on six open model leaderboards, with Porsche, ANYbotics and ADNOC already using the blueprints for driving and industrial inspection.

10/22, 13:00

NVIDIA's open models move into European public services, country by country

NVIDIA rounded up European public-sector projects built on open models, from deepset's expansion of the European Commission's AI@EC platform to Polish medical imaging and agentic systems for 400-plus labor offices, plus sovereign offerings in Germany, France and the UK. The UK and Germany each published million-record localized synthetic persona datasets.