Forecasting hurricane tracks using a complex adaptive system

Abstract

Forecast hurricane tracks using a multi-model ensemble that is comprised by linearly combining the individual model forecasts have greatly reduced the average forecast errors when compared to individual dynamic model forecast errors. In this experiment, a complex adaptive system, the Tropical Agent Forecaster (TAF), is created to fashion a 'smart' ensemble forecast. The TAF uses autonomous agents to assess the historical performance of individual models and model combinations, called predictors, and weights them based on their average error compared to the best track information. Agents continually monitor themselves and determine which predictors, for the life of the storm, perform the best in terms of the distance between forecast and best-track positions. A TAF forecast is developed using a linear combination of the highest weighted predictors. When applied to the 2004 Atlantic hurricane season, the TAF system with a requirement to contain a minimum of three predictors, consistently outperformed, although not statistically significant, the CONU forecast at 72 and 96 hours for a homogeneous data set. At 120 hours, the TAF system significantly decreased the average forecast errors when compared to the CONU.