Europe Deploys NVIDIA Earth-2 Models for Weather AI
Organizations across Europe are deploying NVIDIA Earth-2 open models and tools to customize weather and climate prediction systems with their own local data.
Radwan AbdulhadiEditor and technology writer
Introduction to NVIDIA Earth-2 in Europe
Weather forecasts shape more than daily plans; timely weather information is crucial for energy producers, insurers, and transport operators to plan around changing conditions. While a global forecast can show a storm taking shape, decisions about solar farms, shipping routes, or insured property depend heavily on local developments. To address this need, developers and researchers can access the family of open AI models and tools available through <a href="https://www.nvidia.com/en-us/high-performance-computing/earth-2/">NVIDIA Earth-2</a>.
Running on accelerated NVIDIA computing infrastructure, these advanced technologies support global weather prediction, detailed regional forecasts, and environmental research. Organizations can tailor these models to capture local phenomena that coarser global models might miss.
StormScope EU and Real-Time Demonstrations
StormScope EU is the latest model to join Earth-2 as a regional version of the StormScope model for short-term forecasting, trained specifically over 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 showcased a live StormScope EU pipeline in an interactive weather demo built in partnership with <a href="https://www.earthmover.io/blog/building-a-low-latency-earth-2-nowcasting-pipeline-with-earthmover">Earthmover</a>. The demo utilizes <a href="https://nvidia.github.io/earth2studio/">Earth2Studio’s forecasting examples</a> to run forecasts and Earthmover’s data platform to manage and serve real-time results. These results are updated as soon as new satellite observations arrive every 10 minutes, and Earthmover serves them as map tiles so visitors can explore predictions across Europe without needing to download entire datasets.
Frameworks for Customization and Regional Workflows
Developers can combine Earth-2 models in specialized workflows tailored to regional needs, utilizing StormScope for short-term forecasting and CorrDiff to inject local detail into coarser weather data. Teams can also pick up these model architectures and train them for new environmental applications, such as air-quality modeling.
The open-source <a href="https://developer.nvidia.com/physicsnemo">NVIDIA PhysicsNeMo</a> framework provides essential training and customization tools so engineering teams can build applications that incorporate proprietary data and domain expertise to meet precise regional requirements.
Financial Services and Risk Assessment: AXA
Leading European organizations across different sectors are actively building proprietary intelligence on top of these open models. For instance, <a href="https://developer.nvidia.com/blog/spotlight-axa-explores-ai-driven-hurricane-risk-assessment-with-nvidia-earth-2/">AXA’s hurricane-risk case study</a> highlights how the company is using NVIDIA Earth-2’s FourCastNet 3 to study regional cyclone risk beyond the historical record.
By running simulations across more than 1,000 seasons, AXA generates critical insights that inform broader risk assessments and help customers target prevention efforts effectively.
Enhancing Weather Intelligence and Energy Forecasting
Vaisala Xweather is <a href="https://www.xweather.com/blog/vaisala-xweather-collaborates-with-nvidia-to-deliver-ai-powered-early-warning-for-high-impact-weather">combining Earth-2 with its proprietary observations</a>, lightning data, and forecasting expertise to enhance weather intelligence platforms for government, energy, maritime, transportation, and insurance customers. Its initiatives include adapting StormScope with lightning data to advance short-term forecasting lead times and making these warnings accessible via software-as-a-service offerings and AI-assistant integrations.
Additionally, TotalEnergies is exploring NVIDIA Earth-2 for solar-energy forecasting. The company is evaluating StormScope-based solar-radiation nowcasts at two photovoltaic sites and developing models to provide weather information at subhourly intervals to help anticipate changes in solar-power generation.
Air Quality and Environmental Research
Environmental research is also benefiting from these open technologies. As detailed in the <a href="https://blogs.nvidia.com/blog/uk-air-pollution-research-earth-2/">Manchester’s air-quality story</a>, researchers at the University of Manchester adapted the Earth-2 CorrDiff model for U.K. air-quality modeling.
The team trained the model on the NVIDIA-powered Isambard-AI supercomputer and ran it locally on NVIDIA DGX Spark systems, successfully bringing high-level environmental modeling from a national supercomputer down to the desktop. Meanwhile, Space42 developed SARDiff4Height using CorrDiff and NVIDIA PhysicsNeMo to estimate surface heights from a single radar image while producing uncertainty maps for analysts.
Sources
- NVIDIA BlogPioneers Across Europe Deploy NVIDIA Earth-2 Open Models to Power Real-World Weather and Climate Prediction
Continue chronologically
Related entity coverage
Related stories
Manchester Uses NVIDIA Earth-2 to Forecast UK Pollution
University of Manchester researchers use NVIDIA Earth-2 models to forecast UK air pollution faster and at finer detail for public health planning.
NVIDIA Cloud Partners Scale Across Europe for Sovereign AI
NVIDIA Cloud Partners are expanding regional compute capacity across Europe, the Nordics, Africa, and Central Asia to power sovereign AI infrastructure.
NVIDIA Transforms European Retail With Open Models and Robotics
Discover how European retailers leverage NVIDIA-accelerated open models, digital twins, and physical intelligence to optimize operations and cut costs.
NVIDIA Open Models Power European Public Sector Projects
European public sector projects utilize NVIDIA open models to enhance public services while maintaining strict control over sensitive data and infrastructure.
