The Upscaling Problem: Diagnosing Forecast Error Growth in Next-Generation AI and Physics-Based Weather Prediction Models

Descrizione del progetto

Modelli di previsione meteorologica basati sull’intelligenza artificiale per contrastare schemi di circolazione complessi

I progressi nell’intelligenza artificiale (IA) e lo sviluppo di modelli basati sulla fisica e di scala chilometrica per la risoluzione della convezione profonda hanno portato a sistemi di previsione meteorologica che spesso superano i modelli globali esistenti e offrono una maggiore prevedibilità. Purtroppo, nonostante questi progressi tecnologici, si è osservato che i sistemi basati sull’IA subiscono un calo simile nelle capacità di previsione durante la presenza di complessi modelli di circolazione atmosferica a scala variabile, dove spesso si verificano eventi meteorologici di forte impatto. Sostenuto dal programma di azioni Marie Skłodowska-Curie, il progetto UPDAP realizzerà il primo raffronto sistematico tra modelli basati sulla fisica e modelli basati sull’IA per valutarne l’efficienza nel cogliere l’accoppiamento tra convezione e corrente a getto e il modo in cui tale accoppiamento influisca sulla prevedibilità delle previsioni meteorologiche europee.

Obiettivo

Operational weather prediction is entering a hybrid era, combining rapidly developing global AI-based models with a new generation of kilometer-scale physics-based models that explicitly resolve deep convection. AI-based systems often outperform current global models that parameterize convection on standard forecast skill metrics, while kilometer-scale models promise improved predictability through more realistic representations of mesoscale processes. However, major uncertainties remain regarding how these emerging paradigms simulate and predict complex, scale-coupled circulation patterns. A critical example is the interaction between organized mesoscale convection over North America and the jet stream. In contemporary physics-based models, misrepresentation of this coupling is a well-known driver of sudden degradation in forecast skill over Europe, often coinciding with high-impact weather events. Recent evidence indicates that global AI-based models are also vulnerable to sharp drops in European forecast skill when circulation patterns favor convection–jet stream coupling. Thus, both AI-based and physics-based approaches introduce significant uncertainty for forecast users, particularly during high-impact weather events. This makes it essential to conduct process-level evaluations across modelling paradigms to uncover the mechanisms within these circulation patterns that trigger rapid forecast error growth. UPDAP will provide the first systematic intercomparison of AI-based and physics-based models (including kilometer-scale models) to determine how well they capture convection–jet stream coupling and its influence on European predictability. The project’s outcomes will deliver actionable insight forecast data users, guiding the safe and reliable integration of AI and kilometer-scale physics models into future operations.