Modelling for Improved Flood Forecasting in the Bow River Basin Using Prophet
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".