By combining physics-based data with generative AI tools like DallE, computer scientists at the University of California (UC) San Diego and Allen Institute for AI have created a climate model that is capable of predicting climate patterns over 100 years 25 times faster than existing state-of-the-art models.
Specifically, the Spherical DYffusion model can project 100 years of climate patterns in 25 hours – a simulation that would take weeks for other models. And existing state-of-the-art models need to run on supercomputers, whereas this 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 modeling,” reported the researchers from UC San Diego and the Allen Institute for AI.
The team also highlights that climate simulations are currently very expensive to generate because of their complexity and that, as a result, scientists and policymakers can only run simulations for a limited amount of time and consider only limited scenarios.
Generative AI models
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.
The resulting model starts off with knowledge of climate patterns and then applies a series of transformations based on learned data to predict future patterns.
“One of the main advantages over a conventional diffusion model (DM) is that our model is much more efficient. It may be possible to generate just as realistic and accurate predictions with conventional DMs but not with such speed,” the researchers wrote.
In addition to running much faster than state-of-the-art models, the model is also nearly as accurate without being anywhere near as computationally expensive.
Steps forward
According to the team, there are some limitations to the model that researchers aim to overcome in its next iterations, such as including more elements in their simulations. Therefore, the next steps include simulating how the atmosphere responds to CO2.
“We emulated the atmosphere, which is one of the most important elements in a climate model,” said Rose Yu, a faculty member in the UC San Diego Department of Computer Science and Engineering and one of the paper’s senior authors.
The work stems from an internship that one of Yu’s PhD students, Salva Ruhling Cachay, did at the Allen Institute for AI (Ai2).
In related news, India’s Ministry of Earth Sciences (MoES) recently began exploring the integration of AI technologies into weather and climate forecasting systems and physics-based numerical models. Click here to read the full story.
