Application of ensemble-based machine learning models for investigating the importance of asphalt pavement design factors on IRI

IF 6.1 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement Pub Date : 2026-05-05 Epub Date: 2026-03-09 DOI:10.1016/j.measurement.2026.121087

Abdulraaof H. Al-Qaili, Abdullah I. Al-Mansour, Hamad Al-Solieman

{"title":"Application of ensemble-based machine learning models for investigating the importance of asphalt pavement design factors on IRI","authors":"Abdulraaof H. Al-Qaili, Abdullah I. Al-Mansour, Hamad Al-Solieman","doi":"10.1016/j.measurement.2026.121087","DOIUrl":null,"url":null,"abstract":"<div><div>Asphalt pavement design factors play a critical role in determining the quality and longevity of pavements. Understanding how these factors affect the International Roughness Index (IRI) is essential for optimizing pavement performance and improving road quality. In this study, the importance of asphalt pavement design factors on IRI investigate using ensemble-based machine learning models, providing valuable insights for pavement design and maintenance strategies.</div><div>Ensemble models, specifically Random Forest (RF) and Gradient Boosting (GB), were used to analyze the importance of asphalt pavement design factors on the IRI. These algorithms combine the predictive power of multiple decision trees to increase accuracy and identify critical variables that affect IRI.</div><div>The results of the study demonstrated the influence of hyperparameters on model performance and highlighted the importance of parameter tuning for optimal results. Additionally, the study emphasizes the critical role of factors such as temperature, traffic volume, and pavement age in predicting IRI across different models. SHAP analysis revealed the primary factors influencing IRI, conforming the importance of environmental conditions and material properties.</div><div>This study provide valuable insights into the relationships between asphalt pavement design factors and IRI, offering a roadmap for evidence-based decision making in pavement design and management. The findings can guide stakeholders in prioritizing design factors to optimize pavement quality and overall road performance.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"272 ","pages":"Article 121087"},"PeriodicalIF":6.1000,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263224126007967","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/3/9 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Asphalt pavement design factors play a critical role in determining the quality and longevity of pavements. Understanding how these factors affect the International Roughness Index (IRI) is essential for optimizing pavement performance and improving road quality. In this study, the importance of asphalt pavement design factors on IRI investigate using ensemble-based machine learning models, providing valuable insights for pavement design and maintenance strategies.

Ensemble models, specifically Random Forest (RF) and Gradient Boosting (GB), were used to analyze the importance of asphalt pavement design factors on the IRI. These algorithms combine the predictive power of multiple decision trees to increase accuracy and identify critical variables that affect IRI.

The results of the study demonstrated the influence of hyperparameters on model performance and highlighted the importance of parameter tuning for optimal results. Additionally, the study emphasizes the critical role of factors such as temperature, traffic volume, and pavement age in predicting IRI across different models. SHAP analysis revealed the primary factors influencing IRI, conforming the importance of environmental conditions and material properties.

This study provide valuable insights into the relationships between asphalt pavement design factors and IRI, offering a roadmap for evidence-based decision making in pavement design and management. The findings can guide stakeholders in prioritizing design factors to optimize pavement quality and overall road performance.

查看原文本刊更多论文

应用基于集成的机器学习模型研究沥青路面设计因素对IRI的重要性

沥青路面设计因素对沥青路面的质量和寿命起着至关重要的作用。了解这些因素如何影响国际粗糙度指数（IRI）对于优化路面性能和改善道路质量至关重要。在本研究中，使用基于集成的机器学习模型研究沥青路面设计因素对IRI的重要性，为路面设计和维护策略提供有价值的见解。采用随机森林（Random Forest， RF）和梯度增强（Gradient Boosting， GB）集成模型分析沥青路面设计因素对IRI的影响。这些算法结合了多个决策树的预测能力，以提高准确性并识别影响IRI的关键变量。研究结果证明了超参数对模型性能的影响，并强调了参数调整对优化结果的重要性。此外，该研究还强调了温度、交通量和路面年龄等因素在不同模型中预测IRI的关键作用。SHAP分析揭示了影响IRI的主要因素，符合环境条件和材料性能的重要性。本研究为沥青路面设计因素与IRI之间的关系提供了有价值的见解，为路面设计和管理的循证决策提供了路线图。研究结果可以指导利益相关者优先考虑设计因素，以优化路面质量和整体道路性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Measurement 工程技术-工程：综合

CiteScore

10.20

自引率

12.50%

发文量

1589

审稿时长

12.1 months

期刊介绍： Contributions are invited on novel achievements in all fields of measurement and instrumentation science and technology. Authors are encouraged to submit novel material, whose ultimate goal is an advancement in the state of the art of: measurement and metrology fundamentals, sensors, measurement instruments, measurement and estimation techniques, measurement data processing and fusion algorithms, evaluation procedures and methodologies for plants and industrial processes, performance analysis of systems, processes and algorithms, mathematical models for measurement-oriented purposes, distributed measurement systems in a connected world.