Development and Performance Evaluation of an Artificial Neural Network Model for Estimating Wave Forces on the Pavement behind a Sloping Seawall

In this study, an artificial neural network (ANN) model was developed based on the experimental data obtained from Ko et al. (2022) and Lee et al. (2022) to predict the wave forces acting on the pavement behind a sloping seawall. The ANN models were constructed by varying the number of nodes in the hidden layer and testing various combinations of input variables, both in dimensional and dimensionless forms. The developed neural network models demonstrated excellent wave force prediction performance. In particular, the models established using two heterogeneous sets of experimental data showed significantly better prediction performance than the empirical formulas suggested by Ko et al. (2022) and Lee et al. (2022), respectively.