AI-enhanced flood forecasting: Harnessing upstream data for downstream protection

Abstract

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.

Keywords

• artificial intelligence
• flood prediction
• predictive analytics
• quebec
• water resource management