Application of Artificial Neural Networks to Wave Nowcasting

摘要

In this paper the Artificial Neural Networks (ANN) are used to producea reliable short term (up to 100 s) prediction of the actual sea surfaceelevation, named “wave nowcasting”. This is of primary importance tosupport marine operations of vessels in Offshore Engineering. Thepresent study proposes a combined application of ANN and wavegroupinganalysis based on the Hilbert transform. The observations ofempirical time series are used to verify the performance of this modeland to find the best configuration. The results indicate that the radialbasis function networks provide an effective and accurate tool toforecast the arrival of wave groups at the vessel location.