Abstract:
Techniques based on Artificial Neural Networks (ANN) have been increasingly applied to
predict natural hazards. In this work, a Fuzzy ARTMAP ANN was trained to predict the wave
regime at the entrance and inside the Sines Port, on the Portuguese west coast. In situ
measurements, buoy data and results from numerical modeling were used to train and
validate the ANN. The wave regime was calculated for different points outside and inside the
port. This methodology proved to be able to provide a fast and satisfactory response,
especially useful in the scope of forecast and warning systems.
