Using Machine Learning to Examine Impact of Type of Performance Indicator on Flexible Pavement Deterioration Modeling
Bibliographic record
Abstract
Limited research has been conducted on the application of data analytics to the prediction of the Pavement Condition Index (PCI) of asphalt roads. More importantly, studies comparing the prediction results of these algorithms with other important performance indicators such as the International Roughness Index (IRI) are rare. This paper aims to train machine learning algorithms to predict the PCI and IRI of asphalt pavement using the Long-Term Pavement Performance (LTPP) database. To this end, 30,274 IRI and 3,227 PCI records were queried and prepared to train the models. The first result of using such an unprecedentedly large training set was a higher accuracy level compared to previous works. For example, the highest cross-validation accuracy for predicting the IRI and PCI numeric values (i.e., R2) was 0.95 and 0.84, respectively, which was the result of a random forest regression algorithm. Classification algorithms were used as well. The accuracy of gradient-boosted trees, for instance, reached 88% and 82%, respectively, when predicting the IRI and the PCI. Even higher accuracy levels were achieved after the data were segmented into separate climatic zones, with dry-and-no-freeze region gaining the highest accuracy. Another finding of this research was that the initial IRI has a larger role in the prediction compared to initial PCI. This observation was confirmed by multiple methods including studying the importance factors of a gradient-boosted trees algorithm and relevant correlation matrices of the attributes. Another important finding about the type of performance indicator was that simpler algorithms, such as linear regression or decision tree, can achieve higher accuracy in predicting the IRI.
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 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".