A holistic framework for coastal forecast and evaluation of coastal protection schemes through Integration of hydro-morphodynamic modelling and Artificial Intelligence into the Sand Engine App

There is a growing interest in adoption of Engineering with Nature or Nature Based Solutions for coastal protection including large mega-nourishment interventions. However, there are still many unknowns on the variables and design features influencing their functionalities. There are also challenges in the optimization of coastal modelling outputs or information usage in support of decision-making. Artificial Intelligence, especially deep learning, is a powerful technology that has been rapidly evolving over the last couple of decades and can offer new means of analysis for the coastal science field. Yet, the potential of these technologies for coastal geomorphology remains relatively unexplored with respect to other scientific fields. In the current study, application of Artificial Neural Network is tested in combination with fully coupled hydrodynamics and morphological model (Delft3D) for predicting morphological changes and understanding the behaviour of large mega-nourishment intervention (Sand Engine).

For prediction of morphological change, two sets of deep learning models were tested, one set relying on localized modelling outputs or localized data sources and one set having reduced dependency from modeling outputs and, once trained, solely relying on boundary conditions and coastline geometry. The first set of models provides regression values greater than 0.95 and 0.86 for training and testing. The second set of reduced-dependency models provides regression values greater than 0.84 and 0.76 for training and testing.

For understanding the behavior of sand engines, a holistic framework is proposed which supports the choice of coastal protection schemes through the synthesis of numerical modelling outputs into an Artificial Neural Networking model whose computational efficiency allows the creation of a standalone computer application (Sand Engine App) illustrating the effectiveness of different users’ defined sand engines. In support of this app, twelve Artificial Neural Networking ensemble models structures were trained to predict the influence of different sand engines on water depth, wave height and sediment transports in its vicinity. The ensemble models were trained on simulated data obtained from more than five hundred numerical simulations with different sand-engine designs and different locations along Morecambe Bay conducted in Delft3D. These ensemble models provided good performance with majority of the models having testing regression greater than 0.90. These ensemble models were then packed into a Sand Engine App developed in MATLAB and designed to calculate the impact of different sand engine features on the above variables based on users’ inputs of sand engine designs.