Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest

He, Chunguang; Duan, Ya; Mamat, Tursun; Zhu, Xinglin; Dridi, Mahjoub; Mualla, Yazan; Abbas-Turki, Abdeljalil

doi:10.3390/app16073343

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest

by

Chunguang He

^1,2

,

Ya Duan

^1,2,

Tursun Mamat

^1,2,*

,

Xinglin Zhu

^1,2,

Mahjoub Dridi

³,

Yazan Mualla

³

and

Abdeljalil Abbas-Turki

³

¹

School of Transportation and Logistics Engineering, Xinjiang Agricultural University, 311 Nongda East Road, Urumqi 830052, China

²

Key Laboratory of Transportation and Logistics Engineering in Xinjiang, 311 Nongda East Road, Urumqi 830052, China

³

Université de Technologie de Belfort Montbéliard, UTBM, CIAD UR 7533, F-90010 Belfort, France

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2026, 16(7), 3343; https://doi.org/10.3390/app16073343

Submission received: 6 February 2026 / Revised: 22 March 2026 / Accepted: 26 March 2026 / Published: 30 March 2026

(This article belongs to the Special Issue Intelligent Transportation System Technologies and Applications, 2nd Edition)

Download Versions Notes

Abstract

This study predicts expressway asphalt pavement maintenance decisions using machine learning to overcome the information loss inherent in traditional composite indices like PQI and PCI. Using ten years of inspection data from the G3012 Expressway in Xinjiang, an interpretable Random Forest (RF) model was developed. The methodology integrates permutation-based feature selection, three imbalance mitigation strategies (Balanced Weighting, SMOTE, and Cost-Sensitive Learning), and a rigorous time-aware validation framework. Results indicate that raw distress features—specifically strip repairs, block cracking, transverse and longitudinal cracking—are the most influential predictors, significantly outperforming aggregated indices. The optimized model, using Balanced Weighting and mean imputation, achieved an accuracy of 0.826 and ROC-AUC of 0.853 under strict temporal validation, effectively identifying the minority “repair” class. This research demonstrates that leveraging raw distress data through an interpretable ensemble framework provides a robust, data-driven alternative to threshold-based planning, supporting the transition from reactive to preventive maintenance in complex infrastructure management.

Keywords: asphalt pavement; random forest; maintenance decision prediction; class imbalance; pavement distress; time-aware validation; data-driven modeling

Share and Cite

MDPI and ACS Style

He, C.; Duan, Y.; Mamat, T.; Zhu, X.; Dridi, M.; Mualla, Y.; Abbas-Turki, A. Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest. Appl. Sci. 2026, 16, 3343. https://doi.org/10.3390/app16073343

AMA Style

He C, Duan Y, Mamat T, Zhu X, Dridi M, Mualla Y, Abbas-Turki A. Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest. Applied Sciences. 2026; 16(7):3343. https://doi.org/10.3390/app16073343

Chicago/Turabian Style

He, Chunguang, Ya Duan, Tursun Mamat, Xinglin Zhu, Mahjoub Dridi, Yazan Mualla, and Abdeljalil Abbas-Turki. 2026. "Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest" Applied Sciences 16, no. 7: 3343. https://doi.org/10.3390/app16073343

APA Style

He, C., Duan, Y., Mamat, T., Zhu, X., Dridi, M., Mualla, Y., & Abbas-Turki, A. (2026). Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest. Applied Sciences, 16(7), 3343. https://doi.org/10.3390/app16073343

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI