Can We Trust Evaluations of AI Weather Forecasts for Extremes? How Evaluation Protocols Shape Model Rankings

AI weather models perform competitively with traditional physics-based models at a fraction of the computational cost, and are already used operationally. However, studies reach conflicting conclusions about their ability to forecast extreme weather events, and comparisons across studies are complicated by differing evaluation protocols. We discuss the challenges that arise when comparing AI and physics-based weather forecasts for extreme events. Within a common experimental design, we find that model rankings are highly sensitive to the choice of evaluation metrics: physics-based models perform best when evaluation is restricted to observed extreme events, whereas AI models generally perform better when evaluated using weighted scoring functions. A contingency table analysis shows that AI models underpredict the frequency of extremes, so that their scores are generally dominated by misses, while the physics-based model forecasts extremes more frequently and its scores are dominated by false alarms. Different evaluation metrics penalise these errors differently. Further score decompositions confirm that the score differences arise primarily from miscalibration rather than discrimination ability. This sheds light on the contrasting results in the literature, and highlights the importance of the evaluation metrics used to evaluate AI models.