Forecasting of Extreme Storm Tide Events Using NARX Neural Network-Based Models

The extreme values of high tides are generally caused by a combination astronomical and meteorological causes, as well the conformation sea basin. One place where tide have considerable practical interest is city Venice. MOSE (MOdulo Sperimentale Elettromeccanico) system was created to protect Venice from flooding highest tides. Proper operation protection requires an adequate forecast model tides, which able provide reliable forecasts even some days in advance. Nonlinear Autoregressive Exogenous (NARX) neural networks particularly effective predicting time series hydrological quantities. In this work, effectiveness two distinct NARX-based models demonstrated first input tide, barometric pressure, wind speed, direction, previously observed level values. second instead takes, values, implicitly take into account weather conditions. Both proved capable with great accuracy, greater than that currently used.