Use of random forests regression for predicting IRI of asphalt pavements

•Introducing random forests to predict IRI.•Identifying variables critical to the evolution of IRI.•RFR significantly outperformed the linear regression regarding R2 and RMSE.•The initial IRI is the most critical factor to the evolution of IRI. Random forest is a powerful machine learning algorithm with demonstrated success. In this study, the authors developed a random forests regression (RFR) model to estimate the international roughness index (IRI) of flexible pavements from distress measurements, traffic, climatic, maintenance and structural data. To validate the model, more than 11,000 samples were collected from the database of long-term pavement performance (LTPP) program, with 80% randomly sampled data for training and 20% of them for testing the RFR model. The performance of the RFR model was then compared with that of the regularized linear regression model. The results showed that the RFR model significantly outperformed the linear regression model, with coefficients of determination (R2) greater than 0.95 in both the training and test sets. The variable importance score obtained from the RFR revealed that the initial IRI was the most important factor affecting the development of the IRI. In addition, the transverse cracking, fatigue cracking, rutting, annual average precipitation and service age had important influences on the IRI. Other distresses such as longitudinal cracking, edge cracking, aggregate polishing, and potholes exerted little impact on the evolution of the IRI.