Search

This research devised a cutting-edge artificial intelligence methodology to enhance flood forecasting in Quebec, Canada, an area frequently affected by floods. The core of this project was creating a novel artificial intelligence (AI) model (i.e., Generalized Structure of Group Method of Data Handling) dedicated to the early detection of potential flood events. Utilizing data from two key hydrometric stations, Saint-Charles and Huron, located within the region, the study aggregated data from 15-minute intervals into comprehensive hourly averages. An initial analysis sought to understand the relationship between river flow rates and the environmental factors of temperature and precipitation upstream and downstream. The investigation uncovered intricate relationships among these factors, presenting challenges in accurately predicting floods. To address this, a specialized AI model was developed to translate the flow data from the Huron station to predict potential flooding at the Saint-Charles station. This model, leveraging 48-hour lag data from upstream, was designed to forecast flood events at the Saint-Charles station with lead times ranging from one to eighteen hours. The model demonstrated significant predictive accuracy, with a correlation coefficient surpassing 0.9. Consequently, this innovative AI model emerges as a promising tool for improving Quebec's flood prediction and early-warning systems. [ABSTRACT FROM AUTHOR]

The Ottawa River Watershed is a vast area that stretches across Ontario and Quebec and holds great importance for Canada's people, economy, and collective history, both in the present and the future. The river has faced numerous floods in recent years due to climate change. 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. Indeed, a comprehensive dataset of river flow discharge was generated using a numerical model, encompassing a wide range of potential future floods. This significantly improved the ML training process to generalize the accuracy of results. Utilizing this dataset, a novel ML model called the Expanded Framework of Group Method of Data Handling (EFGMDH) has been developed. Its purpose is to provide decision-makers with explicit equations for estimating three crucial hydrodynamic characteristics of the Ottawa River: floodplain width, flow velocity, and river flow depth. These predictions rely on various inputs, including the location of the desired cross-section, river slope, Manning roughness coefficient at different river sections (right, left, and middle), and river flow discharge. To establish practical models for each of the aforementioned hydrodynamic characteristics of the Ottawa River, different input combinations were tested to identify the most optimal ones. The EFGMDH model demonstrated high accuracy throughout the training and testing stages, achieving an R2 value exceeding 0.99. The proposed model's exceptional performance demonstrates its reliability and practical applications for the study area. [ABSTRACT FROM AUTHOR]

A vital topic regarding the optimum and economical design of rigid boundary open channels such as sewers and drainage systems is determining the movement of sediment particles. In this study, the incipient motion of sediment is estimated using three datasets from literature, including a wide range of hydraulic parameters. Because existing equations do not consider the effect of sediment bed thickness on incipient motion estimation, this parameter is applied in this study along with the multilayer perceptron (MLP), a hybrid method based on decision trees (DT) (MLP-DT), to estimate incipient motion. According to a comparison with the observed experimental outcome, the proposed method performs well (MARE = 0.048, RMSE = 0.134, SI = 0.06, BIAS = -0.036). The performance of MLP and MLP-DT is compared with that of existing regression-based equations, and significantly higher performance over existing models is observed. Finally, an explicit expression for practical engineering is also provided.

This document is a discussion of a research paper titled "Runoff Predictions in a Semiarid Watershed by Convolutional Neural Networks Improved with Metaheuristic Algorithms and Forced with Reanalysis and Climate Data." The discussers express gratitude to the authors for their exploration of deep-learning algorithms to improve runoff predictions in Algeria. The discussion focuses on the impact of confounding parameters in model comparison, such as the number of filters in the convolutional layer, the number of nodes in the fully connected layer, and the choice of activation functions and pooling methods. The discussers also analyze the model complexity and provide minor comments on the original paper. [Extracted from the article]