How can artificial intelligence (AI) help predict weather forecasts with better accuracy and efficiency than current weather forecast methods? This is what a recent study published in Nature hopes to address as an international team of researchers developed a new AI-based method that has the potential to greatly enhance current weather forecast methods while using a fraction of the computing power, time, and energy.
For the study, the researchers developed Aardvark Weather, which utilizes a simple machine learning model to obtain data from a variety of sources, including ground weather stations and satellites, to produce weather forecasts in several minutes. For context, current weather forecast models require hours of data computation and labor, but the researchers discovered that Aardvark outperforms these current forecast methods while using only 10 percent of the data input from current systems.
“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 Dr. Richard Turner, who is a Professor of Machine Learning in the Department of Engineering at the University of Cambridge and Lead Researcher for Weather Prediction at the Alan Turing Institute, and a co-author on the study.
While this study demonstrated Aardvark at the most basic level of weather forecasting, the team aspires to enhance its capabilities within the Alan Turing Institute to provide accurate forecasts for sea ice, oceans, and weather around the globe.
This study comes as climate change continues to wreak havoc on the global population, including more intense weather patterns such as extreme heat and stronger hurricanes. Therefore, Aardvark Weather could help countries around the world be better prepared for extreme weather events well in advance, resulting in reduced damage and loss of life.
How will Aardvark Weather improve weather forecasts in the coming years and decades? Only time will tell, and this is why we science!
As always, keep doing science & keep looking up!
Sources: Nature, EurekAlert!
