Coastal Pavement Maintenance and Rehabilitation Decision Making Based on Both Surface and Subsurface Conditions

Current pavement maintenance decisions in Texas's coastal districts rely mainly on visible surface conditions like cracking and ride quality, which can miss underlying structural problems. This project integrates surface and subsurface data — including results from non-destructive testing — with machine learning models to build a more complete picture of pavement health. The outcome will be a data-driven decision framework that helps transportation agencies intervene earlier, extend pavement life, and allocate limited maintenance budgets more efficiently across coastal road networks vulnerable to hurricanes and flooding.