Adaboost algorithm in artificial intelligence for optimizing the IRI prediction accuracy of asphalt concrete pavement

Abstract

The international roughness index (IRI) for roads is a crucial pavement design criterion in the Mechanistic-Empirical Pavement Design Guide (MEPDG). However, studies have shown that the IRI transfer function in the MEPDG is simply a linear combination of road parameters, so it cannot provide accurate predictions. To solve this issue, this research developed an AdaBoost regression (ABR) model to improve the prediction ability of IRI and compared it with the linear regression (LR) in MEPDG. The development of the ABR model is based on the Python programming language, using the 4265 records from the Long-Term Pavement Performance (LTPP) that include the pavement thickness, service age, average annual daily truck traffic (AADTT), gator cracks, etc., which are reliable data that are preserved after years of monitoring. The results reveal that the ABR model is significantly better than the LR because the correlation coefficient (R2) between the measured and predicted values in the testing set increased from 0.5118 to 0.9751, and the mean square error (MSE) decreased from 0.0245 to 0.0088. By analyzing the importance of variables, there are many additional crucial factors, such as raveling and bleeding, that affect IRI, which leads to the weak performance of the LR model.