Neuro-Fuzzy Logic Model for Breakup Forecasting at Fort McMurray, AB
Bibliographic record
Abstract
At many sites in Canada river breakup presents a source of flooding concern, as the transition from an ice covered river to open water can sometimes be dramatic. Water levels can rise sufficiently quickly to fracture and move the ice cover while the ice is still reasonably strong and an ice jam can form if this moving ice comes to a halt. The safety of residents and property along a river may be compromised by the rising water levels behind a jam or by the water associated with the release of a large ice jam. Fort McMurray AB, is one such site and consequently an extensive database of relevant hydrological, hydraulic and meteorological variables has been created to support ice related research in the Athabasca River basin. Over one hundred variables have been investigated with multiple linear regression methods. Results indicate that several combinations of variables can be used to develop a model for maximum water level to be expected at breakup, but data from three seasons (fall, winter and spring) are needed to produce reasonably reliable forecasts. Therefore, only short term forecasts (only a few days warning) are possible with this model. This paper reports on a more sophisticated non-linear analysis undertaken using fuzzy logic theory, a form of artificial intelligence modeling that can incorporate both expert knowledge and historical occurrences. Here, using a logic rule base derived using artificial neural networks, a breakup forecasting model is developed which provides comparable results using fall and winter data only, thus providing a long lead time forecast (several weeks warning) of potential maximum water levels at breakup.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".