Evaluation of Probabilistic Tropical Cyclogenesis forecasts utilizing Machine Learning Based Methods

The Ensemble-based Globally available Genesis Index for Tropical Cyclones (EGGI-TC) is a novel hybrid dynamical ensemble-statistical model designed to provide probabilistic forecasts of Tropical Cyclogenesis. This model combines machine learning techniques with numerical weather forecast outputs to accurately identify the occurrence of tropical cyclone genesis in dynamical ensemble forecasts. The real-time statistical model operates on the NOAA Global Ensemble Forecast System (GEFS) outputs, enabling the estimation of uncertainty in pre-genesis tracks, as well as providing information on the timing, location, and probability of cyclone genesis. The verification results for previous years have demonstrated the added value of track spread and genesis uncertainty obtained from ensembles, providing valuable insights beyond deterministic forecasts alone. The real-time basin relative reliability and forecast skill metrics of the model will be presented, along with comparison from other ensemble systems and novel AI/ML-based TC genesis outputs. Verification of the recents years including the current 2024 season will show the consistency of these various models across a multi-year sample.