Characterizing the Performance of Interstate Flexible Pavements Using Artificial Neural Networks and Random Parameters Regression

Past studies developed pavement performance models using data from all or multiple states across the United States. This study hypothesized that due to variation in agency practices and work activity profiles, individual pavement performance models should be estimated for each state, using data from its own roadway network, for use in its pavement management system. To test this hypothesis, this study used condition data of Interstate flexible pavements from eight Midwestern states to estimate three models: fixed-parameters regression, random-parameters regression, and artificial neural networks (ANNs). The ANNs model was found to statistically outperform the regression counterparts when estimating pavement roughness across all states. In contrast, the random-parameters model was statistically superior to the ANNs model in some cases when exploring the performance of these models for individual states. The statistical performance of models did not have a consistent trend across all states. Therefore, the application of models, based on data from multiple jurisdictions, could lead to erroneous/nonoptimal maintenance and rehabilitation decisions. Highway agencies are recommended to rely on their own jurisdictional data when developing their pavement performance models.