A SHAP-based framework for visualizing regional heterogeneity in pavement deterioration

Abstract

This study focuses on regional heterogeneity in road-pavement deterioration. Accurate prediction of deterioration is essential for efficient maintenance planning. However, traditional statistical deterioration prediction approaches often have difficulty in capturing the complex nonlinear interactions among deterioration factors and the regional heterogeneity of deterioration, particularly when how regional conditions around road pavement affect the deterioration is uncertain. This study developed a SHAP-based framework for visualizing regional heterogeneity in pavement deterioration. Regional dummy variables are included in the model, and their SHAP values are interpreted as distributions to quantify the influence of regional characteristics on pavement deterioration. A case study using approximately 430,000 inspection records from Japan’s national highways validates the framework. The results reveal that regional location is less influential than primary factors such as time in service and traffic volume, yet its impact is comparable to structural characteristics such as pavement material. Western Japan exhibited overall low deterioration speed, while eastern Japan, especially the Sea of Japan coastal regions, showed high deterioration speed. Overall, the approach visualizes regional heterogeneity in detail and may support region-adaptive maintenance planning.

Keywords

Pavement deterioration / Asset management / Regional heterogeneity / SHAP / Neural network

References

[1] Morikawa H (2004) Current status and challenges of deterioration prediction technology. Concrete Journal (Japan Concrete Institute) 42(5):52–62. [in Japanese] https://doi.org/10.3151/coj1975.42.5_52

[2] Kaito K, Matsumoto K, Kamata T, Kitano Y, Yamanaka A (2023) Simulation of sewer pipe condition using spatial mapping and extraction of rehabilitation and renewal areas. J Japan Soc Civil Eng 79(1):22–00111. [in Japanese] https://doi.org/10.2208/jscejj.22-00111

[3] Kaito K, Kobayashi K, Aoki K, Yoneyama H, Matsumoto K (2021) Evaluation of pavement deterioration rate using spatial mapping: practice in Myanmar. J Civil Eng Pract (JSCE) 77(1):84–100. [In Japanese] https://doi.org/10.2208/jscejppce.77.1_84

[4] Kleiner Y, Rajani B. Comprehensive review of structural deterioration of water mains: statistical models. Urban Water, 2001, 3(3): 131-150.

[5] Frangopol DM, Kallen MJ, Noortwijk JMV. Probabilistic models for life-cycle performance of deteriorating structures: review and future directions. Prog Struct Eng Mater, 2004, 6(4): 197-212.

[6] Avci O, Abdeljaber O, Kiranyaz S, Hussein M, Gabbouj M, Inman DJ. A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mech Syst Signal Process, 2021, 147107077

[7] Llopis-Castelló D, García-Segura T, Montalbán-Domingo L, Sanz-Benlloch A, Pellicer E. Influence of pavement structure, traffic, and weather on urban flexible pavement deterioration. Sustainability, 2020, 12(22): 9717.

[8] Yu B, Xing H, Yan J, Li Y. Small-scale, large impact: utilizing machine learning to assess susceptibility to urban geological disasters—a case study of urban road collapses in Hangzhou. Bull Eng Geol Environ, 2024, 83(11): 1-19.

[9] Lundberg S, Lee S (2017) A unified approach to interpreting model predictions. arXiv preprint: 1705.07874. https://doi.org/10.48550/arXiv.1705.07874

[10] Ministry of Land, Infrastructure, Transport and Tourism (n.d.) National road facility inspection database. https://road-structures-db.mlit.go.jp/

[11] Ministry of Land, Infrastructure, Transport and Tourism (2023) 2021 national road and street traffic survey. https://www.mlit.go.jp/road/census/r3/

[12] Ministry of Land, Infrastructure, Transport and Tourism (2016) Pavement inspection guidelines. https://www.mlit.go.jp/road/sisaku/yobohozen/tenken/yobo28_10.pdf

Funding

Japan Society for the Promotion of Science(25K17699)

RIGHTS & PERMISSIONS

The Author(s)