Mastering Extreme Weather Prediction with AI: Enhancing Forecast Accuracy

In a recent study, scientists evaluated the performance of four AI weather forecast models using Storm Ciarán as a case study. The storm caused extensive damage across Europe in November 2023, including large hail and a tornado in Jersey. The AI models were able to accurately represent the structure of Ciarán, including key features such as the storm's air streams and cloud head. However, all of the models underestimated the maximum wind speeds associated with Ciarán.

The key advantage of using AI models to predict weather is that they are much quicker to produce predictions, anywhere between 10-100 times faster than physics-based models. However, AI models currently require data from physics-based models as an input for their development and to make predictions. Therefore, it is unlikely that we will be moving on from traditional physics-based models anytime soon. Instead, AI models are likely to be increasingly used alongside the traditional models, potentially improving the overall accuracy of weather forecasts.

The study, "Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán," was published in npj Clim Atmos Sci.

Source: <https://www.yourweather.co.uk/news/trending/how-well-can-ai-weather-forecast-models-predict-extreme-events-like-storm-ciaran.html>