Probabilistic forecasts comprehensively describe the uncertainty in the unknown future outcome, making them essential for decision making and risk management. While several methods have been introduce
Regime-stratified probabilistic performance by horizon (aligned evaluation). Outbreak months are defined by , where thr h is the horizon-specific threshold used in the regime split
Centralized: Model trained on pooled data, FL: Federated Learning. The rows indicate where the models were developed, including centralized and federated models, while the columns represent the region
