From data to action in flood forecasting leveraging graph neural networks and digital twin visualization

From data to action in flood forecasting leveraging graph neural networks and digital twin visualization

The paper "From data to action in flood forecasting leveraging graph neural networks and digital twin visualization" by Naghmeh Shafiee Roudbari, Shubham Rajeev Punekar, Zachary Patterson, Ursula Eicker, and Charalambos Poullis has been accepted for publication in Scientific Reports.

TL;DR: Firstly, we present the graph neural network model LocalFloodNet, for predicting future water levels by capturing the interconnections within hydrological systems and between stations. Secondly, we present the prototype of a simulation tool that provides visual insights for disaster prevention and policy-making, demonstrated through a digital twin of Terrebonne, Quebec.

Research paper: https://www.nature.com/articles/s41598-024-68857-y.pdf

Supplementary material: https://static-content.springer.com/esm/art%3A10.1038%2Fs41598-024-68857-y/MediaObjects/41598_2024_68857_MOESM1_ESM.pdf

Video of the simulation tool:

Acknowledgements: This work would not have been possible without the invaluable insights and support provided by Rémi Asselin, Directeur, Direction des technologies de l’information, Ville de Terrebonne; Philippe Hamel, Chef de section, sécurité organisationnelle et réseautique, Ville de Terrebonne; Anh Phuong Tran, Architecte de solutions, Ville de Terrebonne; and Sacha Leprêtre, CTO at Presagis Inc.

Simulation tool screenshots: