StormScope EU and AXA leverage open-source AI for precise 10-minute weather and cyclone risk forecasts

European organisations are deploying NVIDIA Earth-2 open models to generate detailed local weather and climate predictions, moving beyond broad global forecasts to support specific operational decisions in energy, insurance and transport sectors.

Root cause

Timely weather information is crucial for energy producers, insurers and transport operators to plan around changing conditions, as decisions about solar farms, shipping routes or insured property depend on what happens locally rather than just global storm patterns.

Attack path

This section is not applicable to this article as the source material describes a software deployment and research initiative rather than a cybersecurity incident, vulnerability or attack vector. No threat actors or exploits are mentioned.

Affected versions

The source material does not specify software version numbers for the NVIDIA Earth-2 models or associated tools. It references specific model architectures including StormScope EU, FourCastNet 3, CorrDiff and SARDiff4Height, but provides no versioning details for these components.

Mitigation

No mitigation steps are required as this report covers the deployment of new forecasting technologies rather than a security flaw. Organisations are adopting these tools to enhance their predictive capabilities for weather-related operational planning and risk management across various industries.

Why it matters

Teams usually require high-resolution local data to make precise operational decisions, as global models often lack necessary detail. Check whether your current forecasting tools provide sufficient granularity for site-specific planning. Verify that data pipelines can handle frequent updates without significant latency. Ensure that proprietary data integration methods maintain security standards while allowing model customisation for regional environmental conditions.

Background: Threat actors

A threat actor is any individual or group that initiates a cyber attack. This term covers state-sponsored hackers, criminal syndicates, and disgruntled employees. Understanding their motivation helps you predict their methods and prioritise your defensive controls accordingly.

Read the full guide: Threat Actors Meaning: How to Identify and Attribute Cyber Operations

What to do and how to stay safe: NVIDIA

• Review current weather data sources to determine if they provide the local granularity required for critical operational decisions.
• Evaluate whether open-source AI models can be integrated with proprietary data to enhance regional forecasting accuracy.
• Monitor updates to satellite data feeds to ensure timely incorporation of new observations into predictive models.
• Assess the computational resources needed to run localised AI models effectively within existing infrastructure constraints.

Step-by-step guide: Password Policies Examples That Reduce Password Fatigue

General security guidance from the Vector Bulletin newsroom. It is not confirmed advice from the organisations named in this story.

Frequently asked questions

What is StormScope EU?

StormScope EU is a regional version of the StormScope model for short-term forecasting, trained on European weather and climate data using EUMETSAT satellite observations.

How frequently does StormScope EU update forecasts?

The model predicts evolving cloud conditions across 16 Meteosat channels at 10-minute intervals, updating as soon as new satellite observations arrive.

Which organisations are using NVIDIA Earth-2 models?

Organisations include AXA, Vaisala Xweather, University of Manchester, TotalEnergies and Space42, each adapting the models for specific regional and operational needs.