Incorporating Hourly Convective Cloud data into Tropical Cyclone Rapid Intensification Forecasting with Machine Learning

Note that we have only explored a limited number of tunable hyperparameters in the machine learning schemes as the primary aim of this study is to demonstrate the potential impact of integrating very deep convection into tropical cyclone rapid intensification forecasts using machine learning methods. For real‐time operations, the hyperparameters and weights for the individual machine learning schemes should be updated based on available samples prior to each hurricane season.