journal article·2025-02-12Open access

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

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

Applied Sciences· Volume 15· Issue 4

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 (R2) 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.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Explainable Artificial Intelligence (XAI) · Imbalanced Data Classification Techniques · Data Mining Algorithms and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

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

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

Funding

City-University Integration Development Strategy Project of Jinan · National Key Research and Development Program of China · Taishan Scholars Project

References (56)

Show source-provided references
1. A road quality detection method based on the mahalanobis-taguchi system10.1109/ACCESS.2018.2839765 ↗
2. A hybrid wavelet-optimally-pruned extreme learning machine model for the estimation of international roughness index of rigid pavements10.1080/10298436.2020.1776281 ↗
3. Wu, D. (2024). Ride Comfort Prediction on Urban Road Using Discrete Pavement Roughness Index. Appl. Sci., 14.10.3390/app14073108 ↗
4. Al-Mansour, A.I., and Shokri, A.A. (2022). Correlation of pavement distress and roughness measurement. Appl. Sci., 12.10.3390/app12083748 ↗
5. IRI prediction model for use in network-level pavement management systems10.1061/JPEODX.0000003 ↗
6. International Roughness Index prediction model for flexible pavements10.1080/10298436.2018.1441414 ↗
7. Modeling of international roughness index in seasonal frozen area
8. Contribution to the mechanistic-empirical roughness prediction in asphalt pavements10.1080/14680629.2022.2029758 ↗
9. An application of Markov chains to predict the evolution of performance indicators based on pavement historical data10.1080/10298436.2016.1224412 ↗
10. Rigid pavement performance models by means of Markov Chains with half-year step time10.1080/10298436.2017.1353390 ↗
11. Comparison of master sigmoidal curve and Markov chain techniques for pavement performance prediction10.1007/s13369-019-04321-8 ↗
12. Gray system model for estimating the pavement international roughness index10.1061/(ASCE)0887-3828(2005)19:1(62) ↗
13. A methodology for evaluating micro-surfacing treatment on asphalt pavement based on grey system models and grey rational degree theory10.1016/j.conbuildmat.2017.05.181 ↗
14. Asphalt pavement roughness prediction based on gray GM (1, 1| sin) model10.2991/ijcis.d.190808.002 ↗
15. A hybrid model for prediction in asphalt pavement performance based on support vector machine and grey relation analysis
16. IRI Prediction using Machine Learning Models10.37394/232018.2023.11.10 ↗
17. IRI estimation based on pavement distress type, density, and severity: Efficacy of machine learning and statistical techniques10.1061/(ASCE)IS.1943-555X.0000718 ↗
18. Use of random forests regression for predicting IRI of asphalt pavements10.1016/j.conbuildmat.2018.09.017 ↗
19. Machine learning approach for pavement performance prediction10.1080/10298436.2019.1609673 ↗
20. Guo, X., and Hao, P. (2021). Using a random forest model to predict the location of potential damage on asphalt pavement. Appl. Sci., 11.10.3390/app112110396 ↗
21. Research on influencing factors of asphalt pavement international roughness index (IRI) based on ensemble learning
22. Machine learning approach to predict international roughness index using long-term pavement performance data10.1061/JPEODX.0000312 ↗
23. Machine Learning-Based Prediction of International Roughness Index for Continuous Reinforced Concrete Pavements
24. Wang, C., Xu, S., and Yang, J. (2021). Adaboost algorithm in artificial intelligence for optimizing the IRI prediction accuracy of asphalt concrete pavement. Sensors, 21.10.3390/s21175682 ↗
25. Teomete, E., Bayrak, M.B., and Agarwal, M. (2004, January 19). Use of artificial neural networks for predicting rigid pavement roughness. Proceedings of the 2004 Transportation Scholars ConferenceIowa State University, Ames, IA, USA.
26. An ANN model to correlate roughness and structural performance in asphalt pavements10.1016/j.conbuildmat.2016.12.186 ↗
27. Machine learning for pavement performance modelling in warm climate regions10.1007/s13369-020-04398-6 ↗
28. International roughness index prediction of flexible pavements using neural networks10.1061/JPEODX.0000088 ↗
29. Nguyen, H.L., Pham, B.T., Son, L.H., Thang, N.T., Ly, H.B., Le, T.T., Ho, L.S., Le, T.H., and Tien Bui, D. (2019). Adaptive network based fuzzy inference system with meta-heuristic optimizations for international roughness index prediction. Appl. Sci., 9.10.3390/app9214715 ↗
30. Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods10.1080/10298436.2015.1019498 ↗
31. International Roughness Index specifications around the world10.1080/14680629.2016.1197144 ↗
32. A new model for predicting IRI using TabNet with hunter-prey optimization10.1080/10298436.2024.2414070 ↗
33. Federal Highway Administration (2024, November 18). LTPP InfoPave: Long-Term Pavement Performance Data Analysis, Available online: https://infopave.fhwa.dot.gov/Data/DataSelection.
34. Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests10.1016/j.conbuildmat.2019.01.198 ↗
35. Surface layer modulus prediction of asphalt pavement based on LTPP database and machine learning for Mechanical-Empirical rehabilitation design applications10.1016/j.conbuildmat.2022.128303 ↗
36. Analysis of critical factors to asphalt overlay performance using gradient boosted models10.1016/j.conbuildmat.2020.120083 ↗
37. Developing an improved extreme gradient boosting model for predicting the international roughness index of rigid pavement10.1016/j.conbuildmat.2023.133523 ↗
38. García, S., Luengo, J., and Herrera, F. (2015). Data Preprocessing in Data Mining, Springer.10.1007/978-3-319-10247-4 ↗
39. A synergetic locating method for abnormal interval of stacker safety maintenance10.1080/21642583.2018.1543620 ↗
40. Mustaqim, A.Z., Adi, S., Pristyanto, Y., and Astuti, Y. (2021, January 29–30). The effect of recursive feature elimination with cross-validation (RFECV) feature selection algorithm toward classifier performance on credit card fraud detection. Proceedings of the 2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), Yogyakarta, Indonesia.10.1109/ICAICST53116.2021.9497842 ↗
41. Awad, M., and Fraihat, S. (2023). Recursive feature elimination with cross-validation with decision tree: Feature selection method for machine learning-based intrusion detection systems. J. Sens. Actuator Netw., 12.10.3390/jsan12050067 ↗
42. A review of feature selection methods based on mutual information10.1007/s00521-013-1368-0 ↗
43. Elavarasan, D., Vincent PM, D.R., Srinivasan, K., and Chang, C.Y. (2020). A hybrid CFS filter and RF-RFE wrapper-based feature extraction for enhanced agricultural crop yield prediction modeling. Agriculture, 10.10.3390/agriculture10090400 ↗
44. Muthukrishnan, R., and Rohini, R. (2016, January 24). LASSO: A feature selection technique in predictive modeling for machine learning. Proceedings of the 2016 IEEE International Conference on Advances in Computer Applications (ICACA), Coimbatore, India.10.1109/ICACA.2016.7887916 ↗
45. Random forests10.1023/A:1010933404324 ↗
46. On incremental learning for gradient boosting decision trees10.1007/s11063-019-09999-3 ↗
47. Feature selection based on artificial bee colony and gradient boosting decision tree10.1016/j.asoc.2018.10.036 ↗
48. Research on travel time prediction model of freeway based on gradient boosting decision tree10.1109/ACCESS.2018.2886549 ↗
49. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
50. Explainable machine learning model and reliability analysis for flexural capacity prediction of RC beams strengthened in flexure with FRCM10.1016/j.engstruct.2022.113903 ↗
51. Optimization-based stacked machine-learning method for seismic probability and risk assessment of reinforced concrete shear walls10.1016/j.eswa.2024.124897 ↗
52. Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost10.1016/j.compenvurbsys.2022.101845 ↗
53. Lundberg, S. (2017). A unified approach to interpreting model predictions. arXiv.
54. Data-driven interpretable ensemble learning methods for the prediction of wind turbine power incorporating SHAP analysis10.1016/j.eswa.2023.121464 ↗
55. Temperature response of asphalt pavement to low temperatures and large temperature differences10.1080/10298436.2018.1435883 ↗
56. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why should i trust you?” Explaining the predictions of any classifier. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗