Predictability of the Mean Location of Typhoon Formation in a Seasonal Prediction Experiment with a Coupled General Circulation Model

We investigate the feasibility of dynamical seasonal predictions of the interannual variability of the mean location of typhoon formation in the western North Pacific (WNP) and its physical mechanisms during the active typhoon season from June to October. We performed seven-month integrations for 28 years starting from late April using the El Nino Southern Oscillation (ENSO) prediction system of the Japan Meteorological Agency. Typhoons detected with an objective method using model outputs are verified with best track data from the Regional Specialized Meteorological Center, Tokyo. The good overall deterministic skill in predicting the interannual variability of the mean location of typhoon formation fundamentally stems from the ability to predict the interannual variability of the atmospheric circulation in the WNP influenced by ENSO. The interannual variability of indices representing a latitudinal shift of the atmospheric circulation in the WNP is better predicted than that of indices representing a longitudinal shift in this experiment. This difference in skill among these indices provides a physical basis for the difference in prediction skill between the mean latitude and longitude regarding the interannual variability of typhoon formation. Probabilistic predictions also demonstrate the skillful predictions of the mean location of typhoon formation for tercile-based categories. Therefore, both deterministic and probabilistic predictions using our ENSO prediction system provide useful information about the mean location of typhoon formation.