Emulating the estuarine morphology evolution using a deep convolutional neural network emulator based on hydrodynamic results of a numerical model

Abstract Coastal and estuarine areas present remarkable environmental values, being key zones for the development of many human activities such as tourism, industry, fishing, other ecosystem services. To promote sustainable use these services, effectively managing their water sediment resources future conditions is utmost importance to implement operational forecast platforms using real-time data numerical models. These are commonly based on modelling suites, which can simulate hydro-morphodynamic patterns with considerable accuracy. However, in cases, considering high spatial resolution models that necessary develop platforms, a computing capacity also required, namely processing storage. This work proposes artificial intelligence (AI) emulate morphodynamic model results, allowing us optimize computational resources. A convolutional neural network was implemented, demonstrating its reproducing erosion sedimentation patterns, resembling results. The obtained root mean squared error 0.59 cm, 74.5 years morphological evolution emulated less than 5 s. viability surrogating by AI techniques regions clearly demonstrated.