EventsThe 8th International Electronic Conference on Water Sciences
Published
This submission belongs to the session S5. Numerical and Experimental Methods, Data Analyses, Digital Twin, IoT Machine Learning and AI in Water Sciences of the event The 8th International Electronic Conference on Water Sciences
Published date
11 Oct, 2024
Academic Editor
author-avatarJunye Wang
Citation
Victor Joubier, Isa Ebtehaj, Hossein Bonakdari, Classifying River Basin Flood Risk Using AI: A Case Study of the Rideau River, Eastern Ontario, in Proceedings of The 8th International Electronic Conference on Water Sciences, 14 October–16 October 2024, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

Classifying River Basin Flood Risk Using AI: A Case Study of the Rideau River, Eastern Ontario

Victor Joubier 1,2
image
image
1. Ecole Nationale du Genie de l'Eau et de l'Environnement de Strasbourg, 1 Cour des Cigarières, 67000 Strasbourg, France, France
2. Department of Civil Engineering, University of Ottawa, 161 Louis Pasteur Private, Ottawa, ON K1N 6N5, Canada
3. Department of Soils and Agri-Food Engineering, Université Laval, Québec, QC G1V 0A6, Canada, Canada
4. Department of Civil Engineering, University of Ottawa, 161 Louis Pasteur Private, Ottawa, ON K1N 6N5, Canada, Canada
Abstract

Flood risk assessment is crucial for effective water resource management and flood mitigation strategies. This study focuses on detecting and classifying flood risk in the Rideau River basin, located in eastern Ontario, Canada, into four distinct classes. The most significant flood occurred in 2019, surpassing a 100-year flood event, and serves as a stark reminder of how climate change impacts our environment. Considering the limitations of machine learning (ML) models, which heavily rely on historical data used during training, they may struggle to accurately predict such “non-experienced” or “unseen” floods that were not encountered during the training process. To tackle this challenge, our study has utilized a combination of numerical modeling and ML to create an integrated methodology. A comprehensive dataset of river flow discharge was generated using a numerical model, encompassing a wide range of potential future floods. This synthetic dataset ensures that the ML model is trained on a diverse array of scenarios, enhancing its ability to predict flood risks accurately, even for events outside the historical record. The AI model classifies flood risk into four categories: low, moderate, high, and very high. These classifications are based on various factors, including river discharge, precipitation, and temperature data. The integration of AI with numerical modeling provides a robust framework for flood risk assessment, enabling more accurate predictions and better-informed decision-making. The findings highlight the importance of using advanced modeling techniques to address the limitations of traditional ML models in flood prediction. By incorporating a wide range of potential future floods into the training dataset, the study improves the model's ability to predict and classify flood risks under changing climatic conditions. The study underscores the need for adaptive measures to mitigate the increasing flood risks posed by climate change, ensuring the resilience and safety of vulnerable communities along the Rideau River.

Keywords
Flood map
River
Risk
Machine Learning
Decision makers
Ontario
Integrating HEC-RAS and AI for Enhanced Flood Prediction and Management in the Rideau River, Eastern Ontario
Investigating the Effectiveness of Countermeasures in Reducing Local Scour at Bridge Piers Using FLOW-3D