Using Artificial Intelligence for Block Maintenance of Pavement Segments with Similar Degradation Profile
Bibliographic record
Abstract
The Roads Management System of the Ministry of Transportation, Sustainable Mobility and Transport Electrification (MTMDET) of Québec in Canada uses empirical models to simulate the deterioration of the roads' network. This network consists of segments of roads, which are grouped into clusters that have similar degradation profiles. These models are applied in order to predict the roads' deterioration, and to estimate the needs for maintenance, as well as to plan for the necessary budget, according to different investment scenarios. Some of these segments' clusters are not sufficiently well defined by the current explanatory variables, such as the segments' structural categories, the functional classes of roads, and the levels of traffic, in order to be adequate predictors of segments' deterioration. This paper presents a project that was accomplished in order to solve the segments' clustering problem that aims at reducing the variability of the performance indices (PI) of segments that belong to the same cluster, at the same age, or at similar profile of degradation. Thus, the paper focuses on the problem of clustering road segments whose deterioration is similar, by using artificial intelligence techniques. Specifically, it aims at finding the profiles that best describe segments with similar degradation, and the analysis of this degradation over time. A unique segment's identifier, several performance indices (PI), a set of characteristic factors, and the age at the time of collecting an observation, describe each road's segment. The results show that using artificial intelligent techniques leads to better clustering of the roads' segments and to a decrease in the variability of the performance indices within the same cluster.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 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) | 0.000 | 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 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".