Machine learning for developing a pavement condition index

Abstract

Pavement management systems play a major role in preservation of a road network. The core of such systems is pavement condition evaluation. In order to evaluate pavement condition, a pavement condition index is required. To date, several pavement condition indices have been developed; however, they have not been comprehensive, cost-effective, and practical for automated data collection. The objective of this study is to develop a novel pavement condition index expressing comprehensive representation of pavement condition considering structural adequacy, pavement roughness, road safety, and surface distress using a machine learning model. The outcome shows approximately 84% reduction in pavement distress analysis efforts. Moreover, the model with more than 80% accuracy and precision is highly correlated with the Pavement Condition Index (PCI). Thus, the proposed index not only provides similar results to the PCI, but it is also much more cost-effective, practical, and time-saver than the PCI.