Skip to content


Introduction – AI-based NWP emulators:

Announcement: NEW: Our Real-time visualization page for purely AI-based weather models is now available:

Fully AI-based models are emerging for global weather prediction.

These models include: 

The code (and model weights) for some of these models is now available, allowing the community to run them locally and evaluate them. These models include:

These new models raise many questions, including:

At CIRA and NOAA-GSL we seek to address some of these questions. Our current focus:

  1. Develop a research agenda to evaluate AI-based global forecasting models.
  2. Run several of the main models locally, and display them in real-time on a publicly available website. Website has been set up and currently being tested internally. Link will be posted here.
  3. Consider outputs of the models in CIRA’s daily weather briefings to learn about their strengths and weaknesses in forecasting applications.
  4. Identify AI-specific weaknesses of these models.
  5. Evaluate how well existing AI models predict track and intensity of tropical cyclones (TCs)

Recent/upcoming presentations:


CIRA/GSL scientists involved in this project:


Running models locally and visualization:

Evaluation of TC properties:

Introduced models to CIRA weather briefings:

Other members involved in developing the research agenda (in alphabetical order):

Primary contacts:

Imme Ebert-Uphoff (CIRA; and Jebb Stewart (NOAA-GSL;