Abstract

This study investigates the factors influencing safety compliance among airfield workers at Muscat International Airport, with the goal of enhancing adherence to essential safety protocols in this high-risk environment. Safety violations are often driven by behavioral factors rather than management deficiencies, making it crucial to understand what influences compliance behavior. The research was conducted in three phases. The first phase involved a Systematic Literature Review (SLR) to identify key factors affecting safety compliance, which were then categorized. In the second phase, data was collected from airfield staff through an online survey, which was analyzed using Structural Equation Modeling (SEM) and Artificial Neural Networks (ANN). SEM was employed to assess the significance of factors such as the work environment, individual attributes, and organizational culture. The ANN model was developed to create a predictive framework for monitoring compliance over time. The results indicate that the work environment is the most significant factor affecting safety compliance, followed by individual attributes. Based on these insights, a continuous improvement framework is proposed, involving collaboration among the People and Culture, Health, Safety, and Environment (HSE), and Airfield Operations departments. These departments would monitor and address safety behaviors through targeted initiatives informed by the predictive model. This proactive, data-driven approach aims to foster a strong safety culture and enhance operational standards at Muscat International Airport.