Users can generate their own forecasts from a range of state-of-the-art, ML-based, weather forecasting models using the experimental ai-models package. 

Plugins exist for the following models:

Please note that different licences are attached to each of the models, with many not permitting commercial use. Please check that your use is consistent with the licence of the models that you use.

The models require input data (initial conditions) to run. The following inputs are supported:

  • Archive data from ECMWF's Meteorological Archive and Retrieval System (MARS)
  • ERA5 data from the Copernicus Climate Data Store (CDS)
  • ECMWF open data
  • GRIB files

An installation guide for ai-models and example commands are provided on the project Github repository.




  • No labels