Artificial intelligence techniques for pavement performance prediction: a systematic review
Bibliographic record
Abstract
Pavement performance prediction is a major part of a pavement management system that directly impacts the effectiveness of maintenance and rehabilitation decisions. The prediction methods are commonly based on empiricism and traditional statistical models. In recent years, the application of Artificial Intelligence (AI) techniques for pavement performance prediction has gained momentum. These advanced techniques have shown promising results in civil and infrastructure analysis and asset management. With the help of AI, the accuracy and efficiency of pavement performance data analysis are able to be further improved. In this article, a systematic literature review of the existing studies related to pavement performance prediction with supervised AI and ML techniques was conducted. Articles that predicted pavement performance using image processing and computer vision methods were excluded. A total of 1370 peer-reviewed articles from IEEE Xplore, ACM Digital Library, TRID, and Scopus were initially identified, 158 of which met all inclusion and exclusion criteria and were included for the review. PRISMA guidelines were followed for conducting and reporting the review. Neural networks were the most commonly used algorithms, and the majority of the articles focused on flexible pavements and predicting the International Roughness Index (IRI), followed by Rutting. We present a summary of the algorithms, databases, input and output variables used in the previous models and discuss the existing research gaps and directions for future work.
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 | 0.005 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.005 |
| Bibliometrics | 0.010 | 0.010 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".