Artificial intelligence (AI) models developed by tech giants like Google, Nvidia, and Huawei, can quickly and accurately predict the path and intensity of major storms, a new study said on Monday.
According to the study published in the journal npj Climate and Atmospheric Science, weather forecasts based on machine learning (ML) can produce predictions of similar accuracy to traditional forecasts faster, cheaper, and using less computational power.
To investigate this, the researchers analysed November 2023’s Storm Ciaran which hit northern and central Europe.
“AI is transforming weather forecasting before our eyes. Two years ago, modern ML techniques were rarely being applied to make weather forecasts. Now, we have multiple models that can produce 10-day global forecasts in minutes,” Professor Andrew Charlton-Perez, who led the study, said.
The researchers used four AI models created by Google, Nvidia and Huawei, and then compared their results with traditional physics-based models.
These models were able to predict the storm’s rapid intensification and track 48 hours in advance.
To a large extent, the forecasts were “indistinguishable” from the performance of conventional forecasting models, as per the researchers.
In addition, the researchers found that the models accurately captured the large-scale atmospheric conditions that fuelled Ciaran’s explosive development, such as its position relative to the jet stream — a narrow corridor of strong high-level winds.