A study published on Monday found that tech behemoths like Google, Nvidia, and Huawei are using Artificial Intelligence (AI) models to revolutionize weather forecasting.
The study shows how AI-powered weather prediction models can quickly and accurately predict the trajectory and intensity of major storms. It was published in the esteemed journal npj Climate and Atmospheric Science. According to researchers, these AI-based forecasts are quicker, less expensive, and require less processing power than traditional approaches while maintaining the same level of accuracy.
The Storm Ciaran that devastated northern and central Europe in November 2023 is the subject of the research, which is headed by Professor Andrew Charlton-Perez. Using cutting-edge AI models created by Google, Nvidia, and Huawei, the team analyzed the behavior of the storm and compared their results with more conventional physics-based models.
Remarkably, the AI models accurately forecasted the storm’s rapid intensification and trajectory up to 48 hours in advance. According to the researchers, the forecasts were nearly identical to those generated by conventional methods.
“AI is transforming weather forecasting before our eyes,” said Professor Charlton-Perez. Weather forecasts two years ago hardly ever used modern machine learning techniques. These days, a number of our models can generate 10-day global forecasts in a matter of minutes.”
The study emphasizes how well the AI models can represent key atmospheric parameters that influence a storm’s development, such as how a storm interacts with the jet stream, a slender channel of powerful high-level winds.