Development and Implementation of GEFS Based Probabilities for the Tropical Cyclone Logistical Guidance for Genesis (TCLOGG)

This presentation discusses the development and implementation of probabilistic genesis forecasts based on output from the Global Ensemble Forecast System (GEFS). These forecasts are the latest addition to the Tropical Cyclone Logistical Guidance for Genesis (TCLOGG). The developmental dataset was created following the Halperin et al. (2017) methodology utilizing the GEFS Reforecast V12 dataset spanning 2000-2019. This developmental dataset was created using the five GEFSR ensemble members initialized at 00 UTC each day. To generate probabilistic output for TC disturbances, a random forest classification model was employed to develop the ensemble-based statistical models for 2-day, 5-day, and 7-day forecast periods in the Eastern Pacific (EP) and north Atlantic (AL) basins. The final model configuration demonstrated effectiveness with mean absolute errors ranging from 0.15 to 0.28 and ROC AUC scores between 0.63 and 0.75. The GEFS based guidance was implemented in the AL and EP in 2023 and preliminary verification for the season will be shown.