Roughness index forecasts are essential for optimizing pavement rehabilitation and treatment programs. The main objective of this study is to investigate the effect of pavement distress on pavement performance and develop International Roughness Index models (IRI) for dry no freeze regions in the U.S. Data for this research was collected from the Long-Term Pavement Performance (LTPP) database. The data include a total of 138 records of pavement distress with no maintenance and rehabilitation. Based on these data, IRI prediction models were developed using two modelling approaches: Multiple Linear Regression analysis (MLR) and Artificial Neural Networks (ANNs). The proposed models predict the IRI as a function of pavement distress variables such as or including fatigue cracking, block cracking, edge cracking, longitudinal cracking, transverse cracking, potholes, patching, bleeding, and ravelling. This study showed that the (ANNs) model yielded a higher prediction accuracy than the (MLR) model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.