Aardvark Weather was supported by the Alan Turing Institute, Microsoft Research and the European Centre of Medium Range Weather Forecasts.
The Development and Benefits of Aardvark Weather
“Aardvark reimagines current weather prediction methods offering the potential to make weather forecasts faster, cheaper, more flexible, and more accurate than ever before, helping to transform weather prediction in both developed and developing countries,” said Professor Richard Turner from Cambridge’s Department of Engineering, who led the research.
Current forecasting systems can take several hours a day to run and require a significant amount of time and a large team of experts to decipher. Aardvark Weather, however, has replaced the entire weather prediction pipeline with a single, simple machine learning tool. It uses information from satellites, weather stations, and other sensors, outputting data both globally and locally. This approach means that models can be produced in minutes on a desktop computer.
Aardvark Weather Outperforms Traditional Forecasting Systems
The system outperforms the US’s national GFS forecasting system on many variables when just using 10% of the input data of existing systems. “These results are just the beginning of what Aardvark Weather can achieve,” said first author Anna Allen from Cambridge’s Department of Computer Science and Technology. “This end-to-end learning approach can be easily applied to other weather forecasting problems, for example hurricanes, wildfires, and tornadoes.”
Expanding Aardvark Weather’s Potential for Broader Applications
Beyond weather, its applications extend to broader Earth system forecasting, including air quality, ocean dynamics, and sea ice prediction. Aardvark Weather can quickly adapt to produce forecasts for specific industries or locations, such as predicting temperatures for African agriculture. The system has the potential to transform weather prediction in developing countries, where access to the expertise and computational resources required to develop conventional systems is not typically available.
Access and Global Implications of Aardvark Weather
“Unleashing AI’s potential will transform decision-making for everyone from policymakers and emergency planners to industries that rely on accurate weather forecasts,” said Scott Hosking from The Alan Turing Institute. “Aardvark Weather’s breakthrough is not just about speed, it’s about access. By shifting weather prediction from supercomputers to desktop computers, we can democratise forecasting, making these powerful technologies available to developing nations and data-sparse regions around the world.”
Next Steps for Aardvark Weather
The next steps for Aardvark Weather include developing a new team within the Alan Turing Institute, led by Turner, who will explore the potential to deploy Aardvark Weather in the global south and integrate the technology into the Institute’s wider work to develop high-precision environmental forecasting for weather, oceans, and sea ice.
