Anemoi: A New Collaborative Framework for Data-driven Weather Forecasting

Anemoi is an open-source framework co-developed by ECMWF and several European national meteorological services to build, train, and run data-driven weather forecasts. Its primary goal is to empower meteorological organisations to train machine learning (ML) models using their data, simplifying the process with shared tools and workflows.
Designed for modularity and flexibility, Anemoi offers key components for efficient data-driven forecasting. The framework is organised into distinct Python packages covering the entire machine learning lifecycle—from the creation of customised datasets from diverse meteorological sources to the development and training of advanced deep learning graph models. Once a model is trained, Anemoi enables users to run it for inference, using the outputs of physics-based NWP analyses or ensembles as initial conditions, while maintaining comprehensive lineage tracking.
Anemoi has already been applied in experimental operational forecasting, including ECMWF’s Artificial Intelligence Forecasting System (AIFS). It has supported models utilising stretched grid and limited-area configurations. These applications demonstrate Anemoi’s potential to enhance forecasting accuracy by integrating ML techniques into existing systems.
More than just a technical framework, Anemoi represents a collaborative effort among meteorological services, researchers, and technologists, fostering knowledge exchange and innovation.