An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification

Lv, Bin; Gong, Haixia; Dong, Bin; Wang, Zixin; Guo, Hongyu; Wang, Jianzhu; Wu, Jianqing

doi:10.3390/app15041893

Open AccessArticle

An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification

by

Bin Lv

¹,

Haixia Gong

¹,

Bin Dong

¹,

Zixin Wang

²

,

Hongyu Guo

^2,*,

Jianzhu Wang

^2,* and

Jianqing Wu

²

¹

Jihe Operation Management Center, Qilu Expressway Co., Ltd., Jinan 250002, China

²

School of Qilu Transportation, Shandong University, Jinan 250061, China

^*

Authors to whom correspondence should be addressed.

Appl. Sci. 2025, 15(4), 1893; https://doi.org/10.3390/app15041893

Submission received: 28 November 2024 / Revised: 20 January 2025 / Accepted: 10 February 2025 / Published: 12 February 2025

(This article belongs to the Special Issue Pavement Engineering: System, Rehabilitation, and Sustainable Strategies for Long-Term Management)

Download

Browse Figures

Versions Notes

Abstract

This study proposes an explainable extreme gradient boosting (XGBoost) model for predicting the international roughness index (IRI) and identifying the key influencing factors. A comprehensive dataset integrating multiple data sources, such as structure, climate and traffic load, is constructed. A voting-based feature selection strategy is adopted to identify the key influencing factors, which are used as inputs for the prediction model. Multiple machine learning (ML) models are trained to predict the IRI with the constructed dataset, and the XGBoost model performs the best with the coefficient of determination (

R^{2}

) reaching 0.778. Finally, interpretable techniques including feature importance, Shapley additive explanations (SHAP) and partial dependency plots (PDPs) are employed to reveal the mechanism of influencing factors on IRI. The results demonstrate that climate conditions and traffic load play a critical role in the deterioration of IRI. This study provides a relatively universal perspective for IRI prediction and key factor identification, and the outputs of the proposed method contribute to making scientific maintenance strategies of roads to some extent.

Keywords: pavement performance prediction; international roughness index; GBDT; XGBoost; SHAP

Share and Cite

MDPI and ACS Style

Lv, B.; Gong, H.; Dong, B.; Wang, Z.; Guo, H.; Wang, J.; Wu, J. An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification. Appl. Sci. 2025, 15, 1893. https://doi.org/10.3390/app15041893

AMA Style

Lv B, Gong H, Dong B, Wang Z, Guo H, Wang J, Wu J. An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification. Applied Sciences. 2025; 15(4):1893. https://doi.org/10.3390/app15041893

Chicago/Turabian Style

Lv, Bin, Haixia Gong, Bin Dong, Zixin Wang, Hongyu Guo, Jianzhu Wang, and Jianqing Wu. 2025. "An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification" Applied Sciences 15, no. 4: 1893. https://doi.org/10.3390/app15041893

APA Style

Lv, B., Gong, H., Dong, B., Wang, Z., Guo, H., Wang, J., & Wu, J. (2025). An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification. Applied Sciences, 15(4), 1893. https://doi.org/10.3390/app15041893

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

Article Menu

An Explainable XGBoost Model for International Roughness Index Prediction and Key Factor Identification

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI