The continuous increase in maritime transportation produces an increase of the accidents that occur in proximity of ports. Some of such accidents are due to human error and to external factors such as adverse weather conditions. A reliable forecasting of wave climate can mitigate maritime accidents in proximity to the harbour area. The forecast of the weather conditions in port areas are usually evaluated using numerical models. However, these models require high computation costs which makes them inadequate for the nowcasting and the forecasting of wave conditions. To overcome such a limit, this study presents an Artificial Neural Network (ANN) which aims to forecast the wave climate in the port area of Augusta (Sicily). From the analysis of the results, an optimal correspondence of the results obtained by the ANN and the spectral model SWAN is shown.

Artificial Neural Networks for the forecasting of wave climate in proximity of harbour area

Castro E.;Musumeci R. E.;Cavallaro L.;Foti E.
2022-01-01

Abstract

The continuous increase in maritime transportation produces an increase of the accidents that occur in proximity of ports. Some of such accidents are due to human error and to external factors such as adverse weather conditions. A reliable forecasting of wave climate can mitigate maritime accidents in proximity to the harbour area. The forecast of the weather conditions in port areas are usually evaluated using numerical models. However, these models require high computation costs which makes them inadequate for the nowcasting and the forecasting of wave conditions. To overcome such a limit, this study presents an Artificial Neural Network (ANN) which aims to forecast the wave climate in the port area of Augusta (Sicily). From the analysis of the results, an optimal correspondence of the results obtained by the ANN and the spectral model SWAN is shown.
2022
978-1-6654-8574-6
Artificial Neural Networks
maritime accidents
SWAN
wave climate
File in questo prodotto:
File Dimensione Formato  
D_18_MetroXRAINE_2022.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 5.25 MB
Formato Adobe PDF
5.25 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/558025
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact