22 Mar 2023
 | 22 Mar 2023
Status: this preprint is open for discussion.

Rapid Spatio-Temporal Flood Modelling via Hydraulics-Based Graph Neural Networks

Roberto Bentivoglio, Elvin Isufi, Sebastiaan Nicolas Jonkman, and Riccardo Taormina

Abstract. Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive. In the recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. However, most models are used only for a specific case study and disregard the dynamic evolution of the flood wave. This limits their generalizability to topographies that the model was not trained on and in time-dependent applications. 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. The model exploits the analogy between finite volume methods, used to solve the shallow water equations (SWE), and GNNs. For a computational mesh, we create a graph by considering finite-volume cells as nodes and adjacent cells as connected by edges. The inputs are determined by the topographical properties of the domain and the initial hydraulic conditions. The GNN then determines how fluxes are exchanged between cells via a learned local function. We overcome the time-step constraints by stacking multiple GNN layers, which expand the considered space instead of increasing the time resolution. We also propose a multi-step-ahead loss function along with a curriculum learning strategy to improve the stability and performance. We validate this approach using a dataset of two-dimensional dike breach flood simulations on randomly-generated digital elevation models, generated with a highfidelity numerical solver. The SWE-GNN model predicts the spatio-temporal evolution of the flood for unseen topographies with a mean average error in time of 0.04 m for water depths and 0.004 m2/s for unit discharges. Moreover, it generalizes well to unseen breach locations, bigger domains, and over longer periods of time, outperforming other deep learning models. On top of this, SWE-GNN has a computational speedup of up to two orders of magnitude faster than the numerical solver. Our framework opens the doors to a new approach for replacing numerical solvers in time-sensitive applications with spatially-dependant uncertainties.

Roberto Bentivoglio et al.

Status: open (until 11 Jul 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-284', Anonymous Referee #1, 22 Mar 2023 reply
    • AC1: 'Reply on RC1', Roberto Bentivoglio, 20 Apr 2023 reply

Roberto Bentivoglio et al.

Data sets

Raw datasets for paper "Rapid Spatio-Temporal Flood Modelling via Hydraulics-Based Graph Neural Networks" Roberto Bentivoglio and Ron Bruijns

Video supplement

Video simulations for paper "Rapid Spatio-Temporal Flood Modelling via Hydraulics-Based Graph Neural Networks" Roberto Bentivoglio

Roberto Bentivoglio et al.


Total article views: 789 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
505 274 10 789 9 6
  • HTML: 505
  • PDF: 274
  • XML: 10
  • Total: 789
  • BibTeX: 9
  • EndNote: 6
Views and downloads (calculated since 22 Mar 2023)
Cumulative views and downloads (calculated since 22 Mar 2023)

Viewed (geographical distribution)

Total article views: 738 (including HTML, PDF, and XML) Thereof 738 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 04 Jun 2023
Short summary
To overcome the computational cost of numerical models, we propose a deep learning approach inspired by hydraulic models that can simulate the spatio-temporal evolution of floods. We show that the model can rapidly predict dike-breach floods over different topographies and breach locations, with limited use of ground-truth data.