A Hybrid Dynamical‐Statistical Model for Advancing Subseasonal Tropical Cyclone Prediction Over the Western North Pacific Geophysical Research Letters

Tropical cyclone (TC) genesis prediction at the extended ‐range to subseasonal timescale (a week to several weeks) is a gap between weather and climate predictions. The current dynamical prediction systems and statistical models show limited skills in TC genesis forecasting at the lead time of 1–3 weeks. A hybrid dynamical ‐statistical model is developed that reveals capability in predicting basin ‐wide TC frequency in every 10 ‐day period over the western North Paci fica ta2 5 ‐day forecast lead, which is superior to the statistical and dynamical model ‐based predictions examined in this study. In this hybrid model, the cyclogenesis counts for different TC clusters are predicted, respectively, using the statisticalmodels in which the large ‐scale predictors associated with intraseasonal oscillation evolutions are provided