Augmenting the Tropical Cyclone Logistical Guidance for Genesis (TCLOGG) By Introducing a Most Likely Time of Genesis

This talk details the implementation and evolution of the Tropical Cyclone Logistical Guidance for Genesis (TCLOGG) Most Likely Time of Genesis (MLTG) guidance. This new addition addresses a critical gap in TCLOGG, where the initial logistical guidance exhibited biases concerning the timing of tropical cyclone formation. Initially employing a Multiple-Linear Regression (MLR) technique, the original methodology had limitations in predictive accuracy, particularly in the Atlantic basin. To overcome the predictive challenges, this update introduces notable improvements to the MLTG methodology by adopting the Random Forest Regressor (RFR), a more sophisticated machine learning algorithm, as the base statistical model. The development process also includes an expanded dataset that incorporates recent operational changes in numerical weather prediction models and employs a refined predictor selection approach. Implementation of the RFR based MLTG was competed for the 2023 season, and comparison between 2023 and previous seasons will be shown.