Towards AI-enhanced prediction of Mediterranean cyclones

Intense cyclones form frequently in the Mediterranean region, with the potential to cause damage to life and property when they hit highly populated coastal areas. Cyclone impacts are caused by the associated strong winds, flash flooding and storm surge. The social and economic impacts are not limited to the Mediterranean area, as cyclones forming in the region can affect Central Europe. While the skill of weather models to forecast such events has dramatically improved over the last decade, the seasonal predictability of Mediterranean cyclones lags behind due to the limitations on horizontal resolution in probabilistic forecasts requiring a large ensemble of simulationss. Improving the climate prediction at a seasonal scale of those extreme events would be of great benefit for society, enabling better disaster risk management and reducing the economic losses they cause. A better prediction of climate extremes would also directly benefit a number of economic sectors such as the insurance and re-insurance industry. The ambition of the CYCLOPS project is to use Artificial Intelligence techniques to enhance the prediction skills of Mediterranean cyclones in a state-of-the-art Seasonal Prediction System. Here we present initial results making use of AI to link those extreme events to their large-scale driver. The training of different machine learning models is performed using ERA5 reanalysis data. The assessment of model skill is evaluated on the C3S operational seasonal forecast in hindcast mode. The performance of machine learning models of varying complexity (e.g. random forest, artificial neural networks) is evaluated.