An interpretable prediction model for pavement performance prediction based on XGBoost and SHAP

Zhiyuan Luo; Shenglin Li

doi:10.1117/12.2671361

29 March 2023 An interpretable prediction model for pavement performance prediction based on XGBoost and SHAP

Zhiyuan Luo, Shenglin Li

Proceedings Volume 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022); 125940S (2023) https://doi.org/10.1117/12.2671361
Event: Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 2022, Xi'an, China

Abstract

Considering traditional methods’ low accuracy and machine learning methods’ lack of interpretability, this paper proposed a pavement performance model for IRI prediction based on XGBoost, and introduced SHAP to enhance the interpretability of individual features of the model. The data used are from the America LTPP data. Firstly, data cleaning and preprocessing were conducted. Secondly, four prediction models were built based on classical algorithms, namely, LightGBM, XGBoost, SVM, and multiple linear regression. Then, by comparison, it was found that XGBoost performed better. Finally, parameter tuning for this model was performed, with the RMSE as 0.317, MAE as 0.219, and R² as 0.742. In addition, considering the prediction model’s lack of transparency, SHAP is utilized to perform the feature importance analysis and identify the main factors affecting the pavement performance, which can help the highway sector to improve the reliability of their subsequent prediction model analysis.

Citation Download Citation

Zhiyuan Luo and Shenglin Li "An interpretable prediction model for pavement performance prediction based on XGBoost and SHAP", Proc. SPIE 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 125940S (29 March 2023); https://doi.org/10.1117/12.2671361

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available