Machine Learning: Defining Worldwide Cyclone Labels for Training

In this paper we present a procedure for labeling both tropical and extratropical cyclones. The procedure is developed based off of a set of strict heuristics for the purpose of creating a worldwide labeled dataset for cyclones. The heuristics are defined from time, pressure, vorticity, and gradient thresholds without an explicit terrain cut-off. The outputted labeled dataset provides a cyclone center and Region of Interest (ROI) for the area of the cyclone at some given time stamp and this is then applied to GOES 15 water vapor imagery for purposes of a training dataset in deep learning network applications.