A Hybrid Approach to Pavement Performance Prediction in Cold Regions: Machine Learning and Falling Weight Deflectometer Analysis
Bibliographic record
Abstract
Cold region pavements are subjected to extreme environmental conditions, including prolonged periods of low temperatures and repeated freeze-thaw cycles. These harsh conditions accelerate pavement deterioration, leading to an increase in maintenance requirements and significantly higher rehabilitation costs. To address these issues and explore the potential application of sustainable waste materials in pavement design, the Integrated Road Research Facility (IRRF) test section was constructed in Edmonton, Alberta, in 2012. This test section was specifically designed to incorporate sustainable materials, such as bottom ash, polystyrene, and tire-derived aggregates, to reduce environmental impact and enhance pavement durability. Environmental sensors were embedded into the pavement to monitor its performance. However, due to sensor malfunctions over time, the need for enhanced monitoring led to the construction of a new test section in 2022, featuring upgraded instrumentation to ensure improved data accuracy and reliability. This study focuses on temperature data collected from the new test section between June 2023 and December 2024, specifically examining the effects of temperature fluctuations on pavement performance. Using novel machine learning models, this research aims to predict key parameters such as frost depth penetration, as well as the duration and timelines of freeze and thaw cycles, A multi-depth prediction approach was employed to compare both holistic and multi-depth temperature variations from June 2023 to December 2024, ensuring highly accurate insights into the environmental impacts on pavement structures. By incorporating data for the full unbound pavement layers, this approach enhances the predictive capability of the model, providing more detailed insights into temperature variations at multiple depths within the pavement. To assess the long-term performance of the entire test section, including both the insulation layer and tire embankment sections, Falling Weight Deflectometer (FWD) testing was performed in 2015 and 2024. The decade-long comparison of changes in pavement dynamic modulus shows long-term durability and structural behaviour of the pavement. The findings of this study confirm the effectiveness of machine learning models in accurately predicting temperature variations within pavements, a key factor in optimizing pavement design and maintenance strategies. Additionally, the integration of sustainable materials into the test section demonstrates their potential to significantly improve pavement resilience in response to climate change. The results highlight the importance of utilizing innovative materials and advanced modeling techniques in developing adaptive and sustainable pavement management practices. These findings will contribute to more efficient, durable, and environmentally-friendly pavement infrastructure, paving the way for the future of cold-region construction.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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".