Reducing Tropical Cyclone Prediction Errors Using Machine Learning Approaches

Tropical cyclones (TCs) in the North Atlantic region are predictions for the June 1-November 30 season using predictors from Atlantic, Indian and Pacific Oceans sea surface temperature anomalies. Here, the aim is to reduce TC seasonal prediction errors and is realized by applying support vector regression (SVR) to an initial predictor pool and using the model prediction errors to iteratively identify additional attributes that reduce those errors. Prediction errors from this approach are compared with those from an existing, statistical seasonal prediction model, developed at Colorado State University (CSU). The SVR approach was optimized using attribute selection with wrapper selection techniques and by testing various kernels over a range of complexity parameter. Results of the comparison between seasonal SVR and the CSU TC model indicate that proper attribute selection lowers prediction errors significantly. Compared with the CSU model, the SVR model increases correlations between prediction and observed annual TC count from 0.62 to 0.83; the mean absolute error (MAE) is reduced from 2.9 to 1.8 and the root mean squared error (RMSE) drops from 3.8 to 2.7. Furthermore, the approach of using prediction errors to improve machine learning models is flexible and can be adapted readily to other TC basins.