A Spatial-Bayesian Technique for Imputing Pavement Network Repair Data

Pavement construction and repair history is necessary for several pavement management functions such as developing pavement condition prediction models and developing maintenance and rehabilitation (M&R) trigger values based on past repair frequencies. It is often difficult to integrate M&R data with condition data since these data are often stored in disparate heterogeneous databases. This article provides a computational technique for estimating construction and M&R history of a pavement network from the spatiotemporal patterns of its condition data. The technique is founded on Bayesian and spatial statistics and searches pavement condition data in groups of adjacent pavement sections for evidence of repair. The developed technique was applied to a pavement network in Texas and has been found to have a 74% precision and a 95% accuracy in estimating repair history data.