Campos, R.M., Costa, M.O., Almeida, F. and Guedes Soares, C. (2021), “Operational wave forecast selection in the Atlantic Ocean using Random Forests”, Journal of Marine Science and Engineering, Vol. 9(3), 298 (17 pages).

The existence of multiple wave forecasts leads to the question of which one should be used in practical ocean engineering applications. Ensemble forecasts has emerged as an important complement to deterministic forecasts, with better performances at mid- to long- ranges, however they add another option to the variety of wave predictions available nowadays. This paper develops Random Forest (RF) post-processing models to identify the best wave forecast between two NCEP products (deterministic and ensemble). The supervised learning classifier is trained with NDBC buoy data and the RF accuracies are analyzed as a function of the forecast time. A careful feature selection is performed, evaluating the impact of wind and wave variables (inputs) on the RF accuracy. The results showed that the RF were able to select the best forecast only in the short range, using input information of significant wave height, wave direction and period, and ensemble spread. At forecast day-5 and beyond, the RFs could not determine the best wave forecast with high accuracy - the feature space presented no clear pattern to allow a successful classification. The challenges and limitations of such RF prediction for longer forecast ranges are discussed in order to support future studies in this area.

If you did not manage to obtain a copy of this paper: Request a copy of this article

For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications