News
European technologies in security and space
Commissioner Andrius Kubilius' visit to CloudFerro highlights the importance of European technologies for Europe's security and operational readiness
METEO Data Platform
Sovereign data platform for meteorological services
Observations, radar and satellite data and model output in one European cloud. We run the infrastructure; meteorologists run the forecasts and AI.
- Sovereign European cloud
- Works with GRIB, NetCDF and BUFR
- Scalable CPU and GPU compute
Solution Overview
Weather data, from sensor to service, in one place
METEO Data Platform is a European cloud environment for collecting, storing, processing and sharing meteorological data. Secure storage, CPU and GPU compute and workflow tools sit in one place. Services connect existing applications, build AI forecasting and add capacity without replacing their IT estate.
Meteorology's own formats
GRIB, NetCDF, HDF5 and BUFR are processed with established meteorological and open-source tools. Existing workflows connect without unnecessary conversion.
Live and historical data
Near-real-time observations, model output and historical archives sit in one scalable environment. A model run can be verified against decades of observations.
Compute that scales with the run
CPU and GPU capacity and Managed Kubernetes scale up for a model run, an AI experiment or operational processing, and back down when it ends.
From notebook to production
Python, JupyterLab, TensorFlow and PyTorch for building AI models, with the GPU capacity to train, validate and run them in operations.
Built for operational continuity
Backup, redundancy and disaster-recovery options, designed with each service to match how critical it is to forecasts and early warnings.
Key benefits
Focus on forecasts, not on the infrastructure
Every new sensor, finer model and growing archive adds to the infrastructure bill. The platform adds capacity as needed; data and applications stay with the service.
Data control stays in-house
Forecasts and warnings run in EU data centres, under EU law, operated by a European company. Access, data sharing and deployment model are set by the service.
Room to grow, without new hardware
Higher resolution and new satellites don't have to mean a new procurement round. Storage and compute grow with the data, not with the hardware budget.
Technical teams back on meteorology
Less time on hardware maintenance and upgrades, more time supporting meteorologists, researchers and operational forecasters. We run the infrastructure underneath.
Secure collaboration and data sharing
Data moves between national services, research institutes and international partners. Open datasets go public; restricted ones stay restricted.
IT budget matched to demand
Capacity follows actual demand: cloud resources for peak runs, AI development and growing archives, instead of hardware that sits idle between them.
Use Cases
From early warnings to AI forecasts
Built for services that collect more data every year than their own infrastructure can carry.
Data management and exchange
National and international services collect, store, process and share observations, radar and satellite data and model output across interoperable systems.
Early warning and civil protection
National services and crisis centres process observations and forecast models at scale for severe-weather monitoring and warnings on storms, floods and heatwaves.
AI and machine-learning forecasting
Research teams train, test and run AI forecasting models on large meteorological datasets and scalable GPUs, without investing in dedicated hardware.
Defence and national security
Weather data on sovereign infrastructure supports defence organisations in mission planning and situational awareness. Sensitive workloads can run on Private Cloud.
Services for energy, transport and farming
Weather-service providers build forecasts for wind and solar output, route planning and irrigation on the same data and compute.
Start with one workload
Bring one pipeline, archive or model. We'll scope it with your team and show how it would run alongside your current systems.
Architecture
From raw sensor data to shared forecasts
Observations go in at one end. Forecasts, alerts and datasets come out at the other.
0. Security, compliance and performance
Identity and access management, encryption, audit logs and monitoring, with auto-scaling, backup and disaster-recovery options. WMO and OGC standards for external systems.
1. Connect and ingest
Stations, satellite and radar sources and external forecast products connect in batch or near real time, through pipelines built with established meteorological tools.
2. Store and manage
Historical observations, near-real-time data and model output in scalable cloud storage, with metadata catalogues, access policies and data-management tools added as required.
3. Process at scale
CPU and GPU clusters scale with the workload. Distributed processing, the Python ecosystem and JupyterLab do the heavy lifting, in orchestrated, scheduled workflows.
4. Analyse and forecast
Existing meteorological applications and numerical models run alongside new AI forecasting workflows in TensorFlow or PyTorch, on compute that scales with the dataset.
5. Visualise
Weather maps, time-series and anomaly dashboards with GIS integration, built on the platform with the service's own tools or technology partners.
6. Share and distribute
Teams and partners share datasets, models and notebooks, with Git version control. External systems get data through REST or GraphQL APIs, streams and downloads.
Built on CloudFerro products
Compute
Virtual Machines
Run and scale public cloud workloads in EU-based OpenStack data centres. Configure CPU, RAM, storage and OS, manage lifecycle actions.
Compute
GPU Services
Run AI, ML, and HPC workloads on high-performance GPU resources in CloudFerro cloud.
Compute
Spot Instances
Run non-critical, fault-tolerant or interruptible workloads on low-cost OpenStack VMs in European data centres.
Storage
Block Storage
Create and manage persistent block storage volumes, backups, snapshots and volume groups.
Storage
Object Storage
Manage object storage containers and buckets for S3/Swift-compatible data access.
Containers & Serverless
Managed Kubernetes
Deploy production-grade Kubernetes clusters through GUI, CLI or Terraform without managing the control plane yourself.
Databases
Managed Databases
Managed instances of PostgreSQL, MySQL, MariaDB, Valkey, and MS SQL Server. Automated backups, failover, and monitoring.
Private Cloud
Private Cloud
Run your workloads in a fully isolated cloud environment hosted in CloudFerro’s Tier 3 European data centres.
Components
How the platform is put together
CloudFerro's European cloud is the base. Data, processing and AI components are configured on top for each service; specialised applications are built with its teams or technology partners.
Availability and scope of individual components depend on the selected architecture and implementation model.
Cloud infrastructure
- Backup and security options
- Identity and access services
- Managed Kubernetes
- Object, block and file storage
- Virtual machines and GPUs
- Virtual networking
Configurable platform components
- Data-sharing mechanisms
- Workflow orchestration
- Data-access APIs
- Data-processing workflows
- Meteorological data ingestion
- Metadata catalogues
Specialised applications
- Integration with external systems
- Custom meteorological services
- Meteorological dashboards
- Digital twins
- AI forecasting and nowcasting
- Decision-support systems
Customer stories
Proven on Europe's meteorological data
CloudFerro led the WEkEO consortium for EUMETSAT and delivers cloud infrastructure for European meteorological and Earth-observation organisations. The same storage and compute sit under this platform.
WEKEO
The DIAS hybrid cloud computing, built and operated by CloudFerro on behalf of the consortium, led by EUMETSAT, providing access to satellite data, in particular for monitoring the marine, terrestrial, atmosphere and climate environment.
Compliance
Certified at every level
ISO/IEC 27001/27017/27018
Standards for security, privacy and data protection in cloud environments.
Attestation C5
Independently audited cloud security aligned with BSI requirements.
BSI-200-1
Information security based on the established German BSI IT-Grundschutz standard.
EU Facility Security Clearance – Level III
Authorisation to protect EU classified information up to EU SECRET level.
Frequently Asked Questions
What meteorological teams ask first
Control, migration, tools and cost. Anything else, ask our experts.
Other solutions
Payload Data Ground Segment as a Service
Accelerate satellite data processing and delivery with an integrated environment for EO data ingestion, processing, archiving, and dissemination.
EO Data Platform
Process large EO datasets without downloading them, using compute resources available directly where the data resides.
Area Monitoring System as a Service
Monitor agricultural areas and CAP requirements with a managed service powered by Sentinel data and cloud infrastructure.