A Tour Through Anemoi

On this page we present a few entry points to help you get started using Anemoi. The aim here is to help you begin to make progress quickly, rather than being an exhaustive guide of every feature in Anemoi. Try to find the one that best maps onto your use-case and start there, or progress through these in the order below for a more structured tour through the Anemoi framework.

Making predictions with a pre-trained model

If you would like to make predictions with a model that has already been trained, e.g. AIFS Single 1. See the anemoi-inference getting started guide.

Training a new model through configuration

If you would like to train a new model on a sample dataset, making use of building blocks which already exist in the Anemoi codebase. See the anemoi-training getting started guide.

Building a dataset to train a new model

If you would like to go beyond training a model with a sample dataset, e.g. building a new dataset to train a model using new data. See the anemoi-datasets getting started guide.

Contributing use-cases

We would love to make Anemoi even easier for everyone to use. If there are any use-cases you would like to see covered in the future, please consider contacting the developers or creating a pull request to the anemoi repository <https://github.com/ecmwf/anemoi>`_.