Climate modelling gets AI boost

Detailed in this paper, the Spherical DYffusion model can project 100 years of climate patterns in 25 hours, a simulation that would take weeks for other models. In addition, existing advanced models run on supercomputers, but the new model can run on GPU clusters in a research lab. 

“Data-driven deep learning models are on the verge of transforming global weather and climate modelling,” the researchers from the University of California San Diego and the Allen Institute for AI, write. 

Climate simulations are currently very expensive to generate because of their complexity. Consequently, scientists and policymakers can only run simulations for a limited amount of time and consider only limited scenarios. 

One of the researchers’ key insights was that generative AI models, such as diffusion models, could be used for ensemble climate projections. They combined this with a Spherical Neural Operator, a neural network model designed to work with data on a sphere.