article · Transportation Engineering
Predicting pavement performance is essential for maintaining safe and durable road networks. This research develops predictive models for flexible pavement fatigue cracking using several machine learning techniques. A Random Forest feature selection process isolated the fifteen most critical variables influencing road durability. Multiple algorithms were evaluated, including Regression Trees, Gaussian Process Regression, Support Vector Machines, Ensemble Trees, and Artificial Neural Networks. All of these advanced machine learning approaches proved superior to traditional linear regression. Further optimisation demonstrated strong performance across both full and reduced feature sets, confirming the value of careful variable selection. The top-performing optimised model achieved an R-squared value of approximately 0.81, notably surpassing previous empirical forecasting models. Adopting these advanced computational tools supports data-driven decisions that can improve road construction planning, prolong infrastructure lifespan, and raise transport safety standards.
Road networks deteriorate over time under heavy traffic and environmental stress, leading to costly repairs and safety hazards. By using sophisticated machine learning algorithms to accurately predict fatigue cracking, road authorities and engineers can make better-informed, data-driven decisions. This proactive approach helps extend the lifespan of road infrastructure, reduces unexpected failures, and maintains safer travel conditions for the public.
The research enables software-based decision support tools for road maintenance planning and pavement asset management. Target users include civil engineering contractors, transport departments, and infrastructure management agencies. Based on the abstract, the work is at an applied research stage, having validated predictive algorithms against empirical benchmarks on test data, but it has not yet demonstrated integration into commercial pavement management systems or live road inspection workflows.
AI-generated from the published abstract. Always read the original work before citing.
Pavement performance prediction is crucial for ensuring the longevity and safety of road networks. In our extensive study, we employ a diverse array of techniques to enhance fatigue performance models in flexible pavements. The methodology begins with Random Forest feature selection, identifying the top 15 critical variables that significantly impact pavement performance. These variables form the basis for subsequent model development. Our investigation into model performance indicates the superiority of advanced machine learning methods such as Regression Trees (RT), Gaussian Process Regression (GPR), Support Vector Machines (SVM), Ensemble Trees (ET), and Artificial Neural Networks (ANN) over traditional linear regression methods. This consistent outperformance underscores their potential to reshape forecasting accuracy. Through extensive model optimization, we reveal robust performance across both complete and selected feature sets, emphasizing the importance of meticulous feature selection in enhancing forecast accuracy. The accuracy of our best optimized machine learning model is highlighted by its Performance Measurement metrics: RMSE of 22.416, MSE of 502.46, R-squared of 0.80848, and MAE of 8.9958. Additionally, comparative analysis with previous empirical models demonstrates that our best optimized machine learning model outperforms existing empirical models. This work underscores the significance of feature curation in pavement performance prediction, highlighting the potential of sophisticated modeling methodologies. Embracing cutting-edge technologies facilitates data-driven decisions, ultimately contributing to the development of more robust road networks, enhancing safety, and prolonging lifespan.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.treng.2024.100243
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
