A machine learning approach to modelling tropical cyclone wind field uncertainty

This article by Thomas Loridan (Risk Frontiers), Ryan Crompton (Risk Frontiers) and Eugene Dubossarsky (Presciient) was published in the American Meteorological Society Journal on 17th May, 2017.

Abstract: Tropical Cyclone (TC) risk assessment models and probabilistic forecasting systems rely on large ensembles to simulate the track trajectories, intensities and spatial distributions of damaging winds from severe events. Given computational constraints associated with the generation of such ensembles, the representation of TC winds is typically based on very simple parametric formulations. Such models strongly underestimate the full range of TC wind field variability and thus do not allow for accurate representation of the risk profile. With this in mind, this study explores the potential of machine learning algorithms as an alternative to current parametric methods. First, a catalogue of high resolution TC wind simulations is assembled for the Western North Pacific using the Weather Research and Forecasting (WRF) Model. read more