A novel technique for multi-objective sustainable decisions for pavement maintenance and rehabilitation
Bibliographic record
Abstract
To maintain pavement in good condition while considering financial costs and sustainability, it is necessary to develop a comprehensive pavement management plan. Pavement Maintenance and Rehabilitation (M&R) consists of two essential components: firstly, predicting the pavement condition within a specified timeframe, and secondly, employing an appropriate optimization algorithm. This study utilized three ensemble learning techniques including extreme gradient boosting, categorical boosting, and light gradient boosting machine to develop accurate predictions about the pavement condition. Subsequently, the most accurate prediction technique, which was extreme gradient boosting, was combined with non-dominated sorting genetic algorithm III which is a multi-objective metaheuristic optimization algorithm, resulting in a hybrid technique that offers highly accurate multi-objective maintenance and rehabilitation planning. Although previous studies neglected important criteria such as road closure in the optimization process, this study takes into account four objective functions including greenhouse gas emission, M&R cost, pavement condition, and road closure to be minimized over a 5-year program. This process generated 52 non-dominated optimal solutions known as the Pareto front. To compare and rank various optimal maintenance and rehabilitation plans, grey relational analysis was employed. The results suggested that there is a direct correlation between M&R costs and GHG emissions. Minimizing only pavement conditions in the planning can significantly increase GHG emissions, M&R costs, and road closure. Implementing preventive M&R actions can reduce M&R costs and overall road closure while light and medium rehabilitation actions are recommended to optimize the condition of pavements.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".