Emulating the estuarine morphology evolution using a deep convolutional neural network emulator based on hydrodynamic results of a numerical model. Issue 6 (20th September 2022)

• Record Type: Journal Article
• Authors: Weber de Melo, Willian; Pinho, J. L. S.; Iglesias, Isabel
• Is Part Of: Journal of hydroinformatics. Volume 24:Issue 6(2022)
• Page Start: 1254
• Page End: 1268
• Publication Date: 2022-09-20
• Subjects: artificial intelligence -- convolutional neural networks -- Delft3D -- hydro-morphodynamics -- numerical model emulator -- TensorFlow; Hydrology -- Data processing -- Periodicals; Geographic information systems -- Periodicals; Geographic information systems; Hydrology -- Data processing; Electronic journals; Periodicals; 551.480285
• DOI: 10.2166/hydro.2022.068
• Languages: English
• ISSNs: 1464-7141

Abstract

Abstract: Coastal and estuarine areas present remarkable environmental values, being key zones for the development of many human activities such as tourism, industry, fishing, and other ecosystem services. To promote the sustainable use of these services, effectively managing these areas and their water and sediment resources for present and future conditions is of utmost importance to implement operational forecast platforms using real-time data and numerical models. These platforms are commonly based on numerical modelling suites, which can simulate hydro-morphodynamic patterns with considerable accuracy. However, in many cases, considering the high spatial resolution models that are necessary to develop operational forecast platforms, a high computing capacity is also required, namely for data processing and storage. This work proposes the use of artificial intelligence (AI) models to emulate morphodynamic numerical model results, allowing us to optimize the use of computational resources. A convolutional neural network was implemented, demonstrating its capacity in reproducing the erosion and sedimentation patterns, resembling the numerical model results. The obtained root mean squared error was 0.59 cm, and 74.5 years of morphological evolution was emulated in less than 5 s. The viability of surrogating numerical models by AI techniques to forecast the morphological evolution of estuarine regions was clearly demonstrated. HIGHLIGHTS: The application of convolutional neural network (CNN) for the development of an estuarine morphodynamic emulator is still rare. Delft3D hydrodynamic results processed in MATLAB for generating AI model inputs datasets. Python framework for hybrid use of Delft3D and TensorFlow is selected for hydro-morphodynamic models. The assessment of CNN hyperparameter for a morphodynamic problem is an area of focus for future research. A comparison between an emulator and a numerical model can be observed in sedimentation and erosion results.