Artificial intelligence (AI) is rapidly transforming weather and climate science across Europe.
What is changing is not just how models are built, but how information is produced, delivered and used by national meteorological services, public authorities and downstream users. We are shaping this transformation with our Member and Co‑operating States, building on decades of shared investment in data, infrastructure and operational expertise.
Anemoi plays a key role in this transformation. Developed by ECMWF together with several national meteorological services across Europe, Anemoi is a joint European framework enabling the development, training and operation of large‑scale AI models for weather and climate. Rather than focusing on individual models, Anemoi provides shared foundations – datasets, workflows and software infrastructure – that allow AI to move from research into pre‑operational and operational use across national meteorological services and at ECMWF.
From data to decisions: why Anemoi matters
Anemoi supports rapidly evolving machine‑learning (ML) techniques while maintaining the reliability, traceability and robustness required for operational services. Achieving this at scale requires much more than neural network architectures alone. It requires:
- AI‑ready datasets built with deep Earth‑system domain knowledge
- Robust, reusable workflows that run efficiently on distributed European HPC systems
- Integrated tooling for training, inference, verification and monitoring
Anemoi was created to address this shared need. Its focus on end‑to‑end workflows allows new AI capabilities to be developed, tested and deployed collaboratively, without each user having to rebuild the full software stack. This supports innovation while preserving scientific rigour and operational consistency across Europe.
What is Anemoi?
Anemoi is an end‑to‑end software framework for AI weather and climate applications. It covers the full lifecycle from data preparation to model training and large‑scale inference. The framework is modular, Python‑based and designed to run efficiently on modern high-performance computing (HPC) architectures, including EuroHPC systems.
The framework brings together three tightly integrated components.
1. Anemoi datasets
Anemoi produces and manages AI‑ready datasets optimised for ML workloads. These datasets differ fundamentally from traditional “analysis‑ready” data: they are designed around the access patterns, data layouts and throughput requirements needed for large‑scale training and inference. Anemoi datasets draw on:
- ECMWF analyses, forecasts and reanalyses, including the Copernicus ERA5 climate reanalysis dataset
- Observations from satellites and in‑situ networks
- Data contributed by national meteorological services, using formats such as GRIB and NetCDF.
The result is a shared catalogue of ready‑to‑use training datasets, managed and transferred across distributed HPC systems, enabling consistent and reproducible for different applications.
2. Anemoi core: training and ML operations (MLOps)
The Anemoi core provides tooling to train, optimise and monitor AI models at scale. It integrates with widely adopted open‑source tools and MLOps practices, ensuring traceability, reproducibility and quality control throughout the model lifecycle.
This enables models to be trained efficiently on a range of HPC systems – including EuroHPC’s LUMI, Leonardo, Jupiter, MareNostrum 5 and MeluXina – and prepared for pre‑operational and operational environments used by national meteorological services and ECMWF.
3. Anemoi inference
Anemoi also supports parallel inference for large AI models, enabling simulations to be run efficiently at scale. Anemoi inference provides the flexibility to explore and innovate on new applications of AI models for weather forecasting, but also provides the robust, reliable architecture required for daily operations by national meteorological services and ECMWF. This broad capability underpins a growing range of global and regional applications.
A joint European effort, recognised internationally
Anemoi reflects the close collaboration between ECMWF and national meteorological services across Europe, who pool expertise, data and infrastructure to ensure that AI developments remain aligned with national mandates and operational realities.
This collaborative European approach has received international recognition. In 2025, Anemoi was awarded the European Meteorological Society (EMS) Technology Achievement Award, highlighting it as an outstanding example of cooperative innovation enabling the integration of AI into operational forecasting. In the same year, Anemoi received the HPCwire Readers’ and Editors’ Choice Award for Best Use of AI Methods for Augmenting HPC Applications, recognising the successful exploitation of AI and high‑performance computing for weather and climate applications.
Powering European AI weather and climate models
Anemoi provides the shared foundations on which European AI‑based forecasting systems are being built. It underpins the development of our operational Artificial Intelligence Forecasting System (AIFS) and supports a growing family of global or regional AI models developed by national meteorological services, such as AICON, recently operationalised by the German Meteorological Service (DWD).
Within the EU’s Destination Earth initiative, Anemoi plays a key enabling role. It provides the capability to transform digital twin data into AI-ready datasets. It also seamlessly integrates with the Digital Twin Engine, supporting the efficient training of advanced Earth system components, which can then be coupled to form a modular AI-driven Earth system model.
Open, reusable and built for operations
Anemoi is open‑source by design, supporting transparency, trust and reproducibility while enabling a broad ecosystem – from national meteorological services and research institutes to SMEs – to build on shared, high‑quality foundations.
At the same time, it is grounded in key European assets: trusted public data, including ERA5, world‑class HPC infrastructure and deep operational expertise. Combining open frameworks like Anemoi with world-class HPC architecture, such as the EuroHPC systems and EU’s emerging AI factories, strengthens Europe’s capacity to deploy AI responsibly and at scale for weather and climate applications.
Watch the video: Anemoi in action
The video below shows how Anemoi works in practice – from the creation of AI‑ready datasets, through large‑scale training on European HPC systems, to inference and user‑facing applications.