Rapid spatio-temporal flood modelling via hydraulics-based graph neural networks

Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive. In recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. However, most models are only used for a specific case study...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Hydrology and earth system sciences Jg. 27; H. 23; S. 4227 - 4246
Hauptverfasser: Bentivoglio, Roberto, Isufi, Elvin, Jonkman, Sebastiaan Nicolas, Taormina, Riccardo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Katlenburg-Lindau Copernicus GmbH 30.11.2023
Copernicus Publications
Schlagworte:
Analysis
Case studies
Cells
Computational grids
Computer applications
Curriculum
Deep learning
Digital Elevation Models
Evolution
Finite element method
Finite volume method
Flood predictions
Flood waves
Floods
Fluid flow
Graph neural networks
High performance computing
Hydraulics
Machine learning
Modelling
Neural networks
Numerical models
Partial differential equations
Propagation
Shallow water
Shallow water equations
Solvers
Time dependence
Variables
Water depth
ISSN:1607-7938, 1027-5606, 1607-7938
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive. In recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. However, most models are only used 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 shallow water equation–graph neural network (SWE–GNN), a hydraulics-inspired surrogate model based on GNNs that can be used for rapid spatio-temporal flood modelling. The model exploits the analogy between finite-volume methods used to solve SWEs and GNNs. For a computational mesh, we create a graph by considering finite-volume cells as nodes and adjacent cells as being 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 in randomly generated digital elevation models generated with a high-fidelity numerical solver. The SWE–GNN model predicts the spatio-temporal evolution of the flood for unseen topographies with mean average errors in time of 0.04 m for water depths and 0.004 m2 s−1 for unit discharges. Moreover, it generalizes well to unseen breach locations, bigger domains, and longer periods of time compared to those of the training set, outperforming other deep-learning models. On top of this, SWE–GNN has a computational speed-up of up to 2 orders of magnitude faster than the numerical solver. Our framework opens the doors to a new approach to replace numerical solvers in time-sensitive applications with spatially dependent uncertainties.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1607-7938
1027-5606
1607-7938
DOI:10.5194/hess-27-4227-2023