Pavement sure takes a beating. If it’s not road traffic, it’s the weather, particularly extreme weather and climate change. The heat expands the pavement and cold contracts it, resulting in poor road conditions. Our society is very automobile-centric, so reliable roads help foster community resilience and safety. The ability to predict pavement conditions has a big impact on maintenance. However, collecting data, using sensors, and conducting lab experiments can be costly for many communities. Even with all the resources, most communities can only measure a small fraction of road segments annually. In addition, most communities do not have access to the complete set of data, including traffic activities, pavement type, and pavement condition ratings, or PCRs. Without a full picture, it is hard for a model to predict the status of an entire road network.
Researchers Tao Tao and Sean Qian explore using artificial intelligence along with openly available datasets to address these challenges in nine U.S. communities in a new study, “Pavement Condition Prediction for Communities: A Low-Cost, Ubiquitous, and Network-Wide Approach,” in ASCE’s Journal of Infrastructure Systems. The team tested traditional methods of determining PCRs, as well as developed a new modeling set that can predict the change of pavement conditions over any time increment. This low-cost approach of applying open datasets to predictive condition assessment shows promise for enabling better model performance and outcomes. Learn more about how this research can help ensure inclusion and equitable outcomes in pavement management decision-making at https://doi.org/10.1061/JITSE4.ISENG-2378. The abstract is below.
Abstract
Effective prediction of pavement deterioration is critical to forecast infrastructure performance and make infrastructure investment decisions under escalating environmental and traffic change. However, most communities often struggle to undertake such predictive tasks due to limited sensing capacity and lack of granular data. With the pavement condition rating (PCR) data generated from artificial intelligence (AI)-powered computer vision technologies and multiple openly available data sets, we propose a low-cost and ubiquitous approach to predict system-level pavement conditions using nine communities across the US as an example. In addition to predicting absolute PCRs as was done in classical models, we develop another set of models to predict the change in PCRs over any time increment (i.e., time lapse between a PCR observation and retrofit decision point) and compare the results. The findings showed that the proposed low-cost prediction approach yields results comparable to existing studies, demonstrating its promising application in supporting pavement management. Furthermore, the PCR change model indicates that, besides current PCR, weather, road classification, socioeconomics, and built environment attributes are important to predicting PCR change. The interactive impacts also show salient interactive effects between variables and current PCR, offering suggestions on better allocating the limited resources in pavement maintenance projects. Finally, the proposed model could enhance climate resiliency and transportation equity during the pavement management process.
See how this could help your pavement management in the ASCE Library: https://doi.org/10.1061/JITSE4.ISENG-2378.
