Modelling Shoreline Dynamics in Complex Macrotidal Environments Using Neural Networks

Abstract The aim of this work is to test an artificial neural network (ANN) with basic hydrodynamic and morphological variables, in order to assess the effectiveness of such methods in modelling complex beach dynamics. A simple feedforward neural network (FFN) is used to evaluate the impact of selected variables on the prediction of the dynamics of specific shoreline proxies extracted from beach profiles, and to build a predictive model to simulate their positions. The model was trained on datasets from two sites from the French coastal monitoring program DYNALIT, Porsmilin and Vougot covering nearly 20 years. These two sites were selected due to differences in their morphology and hydrodynamics, to assess the performance of FFN over a larger variety of situations. A range of temporalities encompassing 3 days, 7 days, 14 days, and 30 days of selected hydrodynamic and morphological variables were used to study the impact time scales can have on modelled shoreline positions. The shoreline proxies used for Porsmilin and Vougot beaches correspond respectively to the average position of the berm isocontour and the dune vegetation limit isocontour. The FFN included 1 hidden layer and 5 nodes, and was ran 50 times in order to assess the models’ performance. The models were generally successful, with a blind shoreline prediction R of 0.88 for Porsmilin and 0.72 for Vougot. This FFN approach showed all-around better performance than previous beach equilibrium models, which is very encouraging regarding the prediction of future beach morphodynamics and the use of ANN therein.