![]() The GNN then determines how fluxes are exchanged between cells via a learned local function. The inputs are determined by the topographical properties of the domain and the initial hydraulic conditions. For a computational mesh, we create a graph by considering finite-volume cells as nodes and adjacent cells as connected by edges. ![]() The model exploits the analogy between finite volume methods, used to solve the shallow water equations (SWE), and GNNs. In this paper, we introduce SWE-GNN, a hydraulics-inspired surrogate model based on Graph Neural Networks (GNN) that can be used for rapid spatio-temporal flood modelling. ![]() This limits their generalizability to topographies that the model was not trained on and in time-dependent applications. However, most models are used only for a specific case study and disregard the dynamic evolution of the flood wave. In the recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |