Fig. 3

Performance plots of the models, from top to bottom: F1-scores, POD, FAR, TSS, and HSS, for the two datasets using the Hybrid method. Results are shown for the Sweep Frequency dataset (left panel) and the Fixed Frequency dataset (right panel) under F1 optimization. The scores are presented for each of the four models, labeled on the x-axis. Outliers are indicated by circles.