Coupling HEC-RAS and AI for River Morphodynamics Assessment Under Changing Flow Regimes: Enhancing Disaster Preparedness for the Ottawa River
Bibliographic record
Abstract
Despite significant advancements in flood forecasting using machine learning (ML) algorithms, recent events have revealed hydrological behaviors deviating from historical model development trends. The record-breaking 2019 flood in the Ottawa River basin, which exceeded the 100-year flood threshold, underscores the escalating impact of climate change on hydrological extremes. These unprecedented events highlight the limitations of traditional ML models, which rely heavily on historical data and often struggle to predict extreme floods that lack representation in past records. This calls for integrating more comprehensive datasets and innovative approaches to enhance model robustness and adaptability to changing climatic conditions. This study introduces the Next-Gen Group Method of Data Handling (Next-Gen GMDH), an innovative ML model leveraging second- and third-order polynomials to address the limitations of traditional ML models in predicting extreme flood events. Using HEC-RAS simulations, a synthetic dataset of river flow discharges was created, covering a wide range of potential future floods with return periods of up to 10,000 years, to enhance the accuracy and generalization of flood predictions under evolving climatic conditions. The Next-Gen GMDH addresses the complexity and limitations of standard GMDH by incorporating non-adjacent connections and optimizing intermediate layers, significantly reducing computational overhead while enhancing performance. The Gen GMDH demonstrated improved stability and tighter clustering of predictions, particularly for extreme flood scenarios. Testing results revealed exceptional predictive accuracy, with Mean Absolute Percentage Error (MAPE) values of 4.72% for channel width, 1.80% for channel depth, and 0.06% for water surface elevation. These results vastly outperformed the standard GMDH, which yielded MAPE values of 25.00%, 8.30%, and 0.11%, respectively. Additionally, computational complexity was reduced by approximately 40%, with a 33.88% decrease in the Akaike Information Criterion (AIC) for channel width and an impressive 581.82% improvement for channel depth. This methodology integrates hydrodynamic modeling with advanced ML, providing a robust framework for accurate flood prediction and adaptive floodplain management in a changing climate.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| 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".