|
|
Publications
Ré Henriques, M. and Guedes Soares, C. (2024), Accuracy improvement of wave forecasts with Long Short-Term Memory Models, Advances in Maritime Technology and Engineering, Guedes Soares, C. & Santos T.A. (Eds.) Taylor and Francis, London, UK, pp. 671-679.
This study aims at improving the significant wave height and wave peak period predictions of a wave model, using buoy data located at three points offshore the Iberian coast. This is achieved by applying one type of recurring neural network, the Long Short-Term Memory, to model the discrepancies between forecast values and buoy data. After modelling the error time series, the neural network results are used to correct the forecast values. The correlation of the data corrected by the neural network model improves for both variables, when compared with the correlation of the forecast model. The correlation of the corrected data is better for the significant wave height than for the wave peak period.
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
|