EN
The Australian Bureau of Meteorology (Bureau) issues operational tropical cyclone (TC) seasonal
forecasts for the Australian region (AR) and the South Pacific Ocean (SPO) and subregions therein. The forecasts
are issued in October, ahead of the Southern Hemisphere TC season (November to April). Improvement
of operational TC seasonal forecasts can lead to more accurate warnings for coastal communities to prepare
for TC hazards. This study investigates the use of support vector regression (SVR) models, exploring new explanatory
variables and non-linear relationships between them, the use of model averaging, and lastly the
integration of forecast intervals based on a bias-corrected and accelerated non-parametric bootstrap. Hindcasting
analyses show that the SVR model outperforms several benchmark methods. Analysis of the generated
models shows that the Dipole Mode Index, 5VAR index and the Southern Oscillation Index are the most
frequently selected as explanatory variables for TC seasonal forecasting in all regions. The usage of ENSOrelated
covariates implies that definitions of regions and subregions may have to be updated to achieve optimal
forecasting performance. Overall, the new SVR methodology is an improvement over the current linear
discriminant analysis models and has the potential to increase accuracy of TC seasonal forecasts in the AR
and SPO.