**4. Conclusions**

A simplified real-time forecast method and a simplified method for the estimation of return levels of storm surge in semi-enclosed basins are proposed. Both the two approaches are mixed. Indeed, results coming from a physics-based approach are corrected by means of statistical corrections.

In both cases, the strategy is to estimate the dynamic response function of the basin to a unit wind stress. These functions may be used, following the theory of

*Simplified Methods for Storm Surge Forecast and Hindcast in Semi-Enclosed Basins: A Review DOI: http://dx.doi.org/10.5772/intechopen.92171*

linear dynamic systems, to compute the response of a considered semi-enclosed basin using whatever wind time series.

In this way, only the wind field role is considered, and the pressure field is not. In order to take into account all the meteorological parameters inducing the storm surge, a statistical correction for both models is proposed.

In the case of forecast models, the statistical correction have been made using a series of artificial neural networks trained with (a) the residual raw level time series, (b) recent residual level estimated at the POI on the basis of the measurements collected during 24 h before the forecast time and (c) the forecasted pressures along the basin as input neurons.

For the hindcast method, instead, the pressure field has been considered using the pressure anomaly and operating a statistical correction using a calibration coefficient.

The approaches allow to reduce the computational costs since the numerical simulations have to be done once and for all for each considered basin.

The two methods have been applied to two different points of interest in the Adriatic Sea revealing in both cases good reliability of the obtained results compared to their simplicity.

It has to be noticed that these approaches are devoted to study storm surges in the semi-enclosed basins and are not able to correctly reproduce storm surges due to very rapid meteorological events (i.e. hurricanes).
