A SURROGATE-AIDED MODEL FOR NEARSHORE WAVE ESTIMATIONS OVER THE SHALLOW NGOM WATERS

Abstract:

Reliable and accurate shallow water wave estimations are the very fabric for safe navigation, understanding sediment transport patterns and design of coastal infrastructures. Long-term and real-time wave measurements are usually not available in the nearshore-ocean and coastal marine environments on a regular basis. Nearshore wave characteristics are highly affected by bathymetric features which are dynamic and usually not well resolved in shallow water areas. Therefore, numerical simulations and/or surrogate models are to be adopted to obtain reliable wave estimations in nearshore locations of interest. On the other hand, the most important role in obtaining reliable simulated wave data is played by well-established and accurate simulated wind field data sets over the study area. Numerical weather prediction models can be used as a tool to estimate marine surface winds and for providing input parameters to the sea surface wave and ocean circulation numerical models. It is while, the model results which are to be verified with observational data may show considerable bias from the real situation in certain circumstances; something which can be attributed to the dynamic and unstable nature of the atmospheric phenomena affecting simulation results.

The present study aims to develop a surrogate aided model for nearshore/shallow water wave predictions over the Northern Gulf of Mexico (NGoM) waters. To this end, a set of wind field data over the NGoM was adopted from ECMWF Global Model together with real field wave observations from nearshore and offshore areas of NGoM. An Artificial Neural Network was employed to establish a surrogate-aided model for providing reliable shallow water wave estimations. The developed model was trained, assuming wind data and offshore wave parameters at certain locations as the input to the network and wave observations at selected nearshore station as the target. The model has been trained for periods of observational data availability and validated for other periods that has not been considered for training phase. The results obtained from the surrogate model are in agreement with the observations. A decision support system is developed based on the wave estimation surrogate model results to estimate the safe periods of time for navigation in the desired nearshore areas.