Toward an AI-enhanced hydro-morphodynamic model for nature-based solutions in coastal erosion mitigation

Abstract

In the application of sustainable Nature-based Solution (NbS) for coastal engineering, a significant challenge lies in determining the effectiveness of these NbS approaches in mitigating coastal erosion. The efficacy of NbS is influenced by various factors, including the specific location, layout, and the scale of implementation. This study integrates artificial intelligence (AI) with hydro-morphodynamic numerical simulations to develop an AI-based emulator focused on predicting Bed Level Changes (BLC) as indicators of erosion and deposition dynamics. Specifically, we explore the influence of seagrass meadows, varying in starting depth (hs) and depth range (hr), on coastal erosion mitigation during storm events.

The framework leverages a hybrid approach combining the SCHISM-WWM hydrodynamic model with XBeach for simulating 180 depth range and starting depth combination (h_r-h_s) scenarios along the Norderney coast in the German Bight. A Convolutional Neural Network (CNN) architecture is employed with dual inputs—roller energy and Eulerian velocity—to predict BLC efficiently. The CNN demonstrates high accuracy in replicating spatial erosion patterns and quantifying erosion volumes, achieving an RMSE of 3.47 cm and an R² of 0.94 during validation.

This innovative integration of AI and NbS not only reduces computational costs associated with traditional numerical modelling but also enhances the feasibility of What-if Scenarios applications for coastal erosion management. The findings underscore the potential of AI-driven approaches to optimize seagrass transplantation layouts and inform sustainable coastal protection strategies effectively. Future advancements aim to further streamline model integration and scalability, thereby advancing NbS applications in enhancing coastal resilience against environmental stressors.