Search

Deltaic tidal flat is an important ecosystem that supports the livelihoods of millions of people globally. Due to the complexity and stochastic nature of tidal flat development, it is a challenging task to predict the tidal flat prograding limit accurately. In this study, we fill out this gap from the perspective of numerical simulation by focusing on the tidal flat extension limit of Nanhui Shoal (NHS), the largest marginal shoal of the Changjiang Estuary. Our results suggest that the tidal flat of NHS extended 29.16 m/y seaward in 1989-2002, had a rapid progradation of 158.08 m/y in 2002-2012 and a retreat rate of 26.88 m/y in 2012-2019, while the fluvial sediment supply decreased 56.78% from 1989-2002 to 2003-2012 and another 20.68% from 2003-2012 to 2013-2019. During the 1989-2002 period, the advancing rate of the -5misobaths followed a Gaussian frequency distribution, in agreement with simulation results of cellular automata. We suggest that in the absence of human perturbations, as the sediment input to NHS declines to the threshold of 0.01×108 t/y, the seaward advance of tidal flats may significantly slow down. However, human interferences generated large uncertainties on the development tendency of the NHS. [ABSTRACT FROM AUTHOR]

As climate-driven risks for the world's coastlines increase, understanding and predicting morphological changes as well as developing efficient systems for coastal forecast has become of the foremost importance for adaptation to climate change. Artificial Intelligence is a powerful technology that has been rapidly evolving recently 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. This article investigates the use of Artificial Neural Networks and Bayesian Networks in combination with fully coupled hydrodynamics and morphological models (Delft3D) for predicting morphological changes and sediment transport along coastal systems. Two sets of Artificial Intelligence models were tested, one set relying on localized modeling outputs or localized data sources and another 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, respectively. The second set of reduced dependency models provides regression values greater than 0.84 and 0.76 for training and testing, respectively. Our results highlight the potential of AI and statistical models for coastal applications. [ABSTRACT FROM AUTHOR]