From the source
Ai2 is starting a climate modeling initiative with three-year, multimillion-dollar funding from Google.org and technical support from
Google Research, to build NeuralGCM+, an open-source model for faster, more reliable climate projections.
- The work extends Google Research's NeuralGCM, which uses physical equations for large-scale dynamics and AI for smaller-scale processes such as cloud formation and rainfall.
- Ai2 will extend it to simulate the atmosphere and ocean together, capturing how oceans absorb and redistribute heat, a major influence on long-term climate.
- Google Research has been developing NeuralGCM for nearer-term forecasts over weeks to months, while Ai2's focus will be climate trends over years to decades, including how rainfall and water availability could change through mid-century in regions such as the southwestern United States.
- Ai2 plans to develop NeuralGCM+ along three fronts: linking it with an ocean and sea-ice model for stable simulations spanning decades, adding more established physics to test warmer climates, and releasing models and frameworks with documented workflows for outside researchers.






