Stochastic models of tropical cyclone genesis in the Philippine Sea

Climate change has influenced the anomalies of extreme weather events, including tropical cyclones (TCs), strong wind, flood and landslide. The investigation of TC genesis is of great significance in evaluating TC activity in order to mitigate TC - induced risks. This study focuses on developing the stochastic models to simulate TC geneses over the Philippine Sea, considering seasonal effects. The historical TC data, including TC number and genesis positions, were obtained from the Japanese Meteorology Agency (JMA) over the period 1951 - 2020. To select the optimal probability distributions to fit the observed TC data, the good-of-fit tests were performed throughout three metrics, namely Mean Absolute Error; Normalized Mean Squared Error and Correlation Distance. Moreover, the Chi-square test and the Kolmogorov - Smirnov test were utilized to evaluate the homogeneity of the selected probability distributions to the observed TC data. The statistical analysis on TC characteristics presented that most TC geneses occurred in the latitudinal belt 8 degrees N - 30 degrees N from July to October, called the active season (AS). Meanwhile, there was a low TC genesis frequency distributed in the region south of 15 degrees N from November to June, called the inactive TC season (IAS). The stochastic models showed the distributions of the observed TC number followed Negative binomial (NB) distribution for the two seasons. Generalized extreme value (Gev) distribution fitted TC genesis longitude well for the inactive season and fitted TC genesis latitude well for the active season. In the active season, the kernel distribution was appropriate for genesis longitude, whereas in the inactive season, it was suitable for genesis latitude. Monte Carlo simulations for 1000 years indicated the similarities in the geographical distributions of the simulated TC geneses and the historical ones for the inactive and active seasons.Data Availability Statement: The Best Track data can be accessed from the Japanese Meteorology Agency. Data of the Philippine Sea boundary can be accessed from Marine Regions, governed by the Flanders Marine Institute.