Fig. 9From: Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric modelPOD and FAR (pth = 1.0 and pth = 0.6) and the number of data (training and test data) for each month in each basin. Note that the POD cannot be defined when the number of TCs is zero according to Eq. (2). In the same manner, the FAR cannot be calculated when the positive prediction area is zero, according to Eq. (3)Back to article page