Articles | Volume 1, issue 2
Research article
13 Jul 2020
Research article |  | 13 Jul 2020

Robust predictors for seasonal Atlantic hurricane activity identified with causal effect networks

Peter Pfleiderer, Carl-Friedrich Schleussner, Tobias Geiger, and Marlene Kretschmer

Data sets

IBTrACS - International Best Track Archive for Climate Stewardship K. Knapp, H. Diamond, J. Kossin, M. Kruk, and C. Schreck (IBTrACS Science Team)

ERA5: Fifth generation of ECMWF atmospheric reanalyses of the global climate Copernicus Climate Change Service (C3S)

JRA-55: Japanese 55-year Reanalysis, Daily 3-Hourly and 6-Hourly Data Japan Meteorological Agency (JMA)

Model code and software

atlantic_ace_seasonal_forecast P. Pfleiderer

TIGRAMITE - Causal discovery for time series datasets J. Runge

Short summary
Seasonal outlooks of Atlantic hurricane activity are required to enable risk reduction measures and disaster preparedness. Many seasonal forecasts are based on a selection of climate signals from which a statistical model is constructed. The crucial step in this approach is to select the most relevant predictors without overfitting. Here we show that causal effect networks can be used to identify the most robust predictors. Based on these predictors we construct a competitive forecast model.