Utilization of Advanced Modeling Techniques for Improving the Existing Airfield Pavement Management System Considering Structural and Functional Condition Indices

Abstract Airport authorities constantly collect pavement condition data to select construction and maintenance alternatives. The current Federal Aviation Administration (FAA) Advisory Circular 150/5380-7B recommends using Pavement Condition Index (PCI) to assess airfield pavement condition for planning Maintenance and Rehabilitation (M&R) treatments. However, PCI can mask the root cause of pavement deterioration and result in inadequate M&R recommendations. Furthermore, the regression-based nature of existing airfield pavement condition assessment models is unsuitable for predicting pavement performance as a function of multitude features. The objective of this study was to enhance the existing PCI-based approach by evaluating the condition of asphalt concrete pavement of key airport components (runway, taxiway, and apron) using three indices: PCI, Structural Condition Index (SCI), and Foreign Object Debris/Damage (FOD). Two machine learning models were developed to predict the SCI and FOD based on the corresponding PCI values and key project conditions such as pavement age, branch use, pavement surface type, inspection year, aircraft average operation per day, air traffic composition (%General, %Transient, %Military, and % Air Taxi aviation), mean annual temperature, annual cumulative rainfall, annual cumulative rainfall days, and annual cumulative snowfall. Three machine learning algorithms, namely, ensemble learning method, CatBoost, and LightGBM were used to train and validate the models. A total of 2,505 pavement sections obtained from 89 airport networks in seven US states were included in the analysis. CatBoost consistently outperformed in predictive accuracy, establishing it as the most robust model for advancing data-driven airfield pavement management and optimizing M&R decision-making.