Modelling for Improved Flood Forecasting in the Bow River Basin Using Prophet

Abstract

Listen

Translate article

The catastrophic flood of the Bow River in 2013 had a significant impact on Calgary, Canada, and citizen's lives, showing the need for early warning systems and preparedness ahead-of-time. AI-based models that integrate climate and historical flow data, using the Prophet algorithm as applied in this research, demonstrate high accuracy in predictions for 15-, 10-, 5-day-ahead and 24-hour-ahead during extreme events in the Bow River, Banff. The predictions 5-day-ahead and 24-hour-ahead are 96.1% and 98.8% accurate, respectively, to the actual event on June 21st, 2013, as a particular case study. The Prophet algorithm shows significant benefits that maintain consistent nonlinear trends with daily, and weekly seasonality. This model also works with diverse components such as trends with high accuracy and greatly improves results using, for example, the GMDH algorithm. A comparison of evaluation metrics for the GMDH and Prophet models indicates that the GMDH model shows R², RMSE, and MAE values of 0.64, 46.8, and 6.70 respectively, with a disparity in accuracy and an absence of trend between the target and the dependent variables. The GMDH model performs well with a timestep of 17 h, but the accuracy significantly decreases with a timestep prediction of 120 h or 5-day-ahead, rendering the model's utility minimal. In contrast, the Prophet model features better prediction of time series data with higher evaluation metrics of R², RMSE, and MAE values of 0.97, 41.7, and 3.19, respectively.