Improving The Planning and Scheduling of Road Maintenance Projects Using Crack and Climate Data Analysis

Road infrastructure in dry and semi-dry climates has become more susceptible to rapid deterioration because of climate pressures and changing pavement performance. This research proposes a data-based predictive model to help assess road conditions and inform maintenance strategies by combining long-term climatic variables (ex, effective rainfall, evapotranspiration, climatic water balance) with pavement performance data collected from vibration sensors and static structural assessments; both datasets are analyzed together using a Random Forest classification model. The results show that incorporating climate data into the analysis produces improvement in the estimated timeliness of construction activity and could promote proactive maintenance through adaptation to climate conditions. Methodologically, this finding is significant in that it creates a single machine-learning framework by combining several independent data sources (i.e., dynamic measure of sensing) into one value using a quantifiable climate index. Practically, this research provides decision-making support for maintenance timing, decreases uncertainty in deterioration estimates, and improves the sustainability of road networks in dry climates.