Airport terminals are complex sociotechnical systems, in which humans interact with diverse technical systems. A natural way to represent them is through agent-based modeling. However, this method has two drawbacks: it entails a heavy computational burden and the emergent properties are often difficult to analyze. The purpose of our research is therefore to accurately abstract and explain the dynamics of airport terminal operations by means of computationally efficient and interpretable surrogate models, based on an existing detailed agent-based simulation model. We propose a methodology consisting of two stages. Stage I involves the development of faithful surrogates. A sample is collected according to an active learning strategy, upon which Gaussian process regression, higher-order polynomials, gradient boosting, and random forests are fitted. Stage II then applies state-of-the-art techniques from the emerging field of explainable artificial intelligence to interpret and understand these models. Both model-agnostic and model-specific methods are considered, and their results are synthesized in order to explain the emergent properties. We prove the efficacy of this approach by conducting two case studies on AATOM, an existing Agent-based Airport Terminal Operations Model. The first case study examines the total expenditure on discretionary activities, such as shopping and dining. A combination of poor staffing strategies and high occupancy rates on certain flights was found to disrupt the terminal journey of passengers on subsequent flights. As a result of these knock-on phenomena, less free time is left for discretionary activities, which has a negative effect on the total expenditure. The second case study examines the throughput of security checkpoints. While throughput increases with passenger numbers, a clear point was observed where the checkpoint reaches its maximum capacity. This leads to longer queues and therefore higher waiting times. It even goes so far as to put passengers at risk of missing their flight, especially with poor staffing strategies. Altogether, we clearly observed the preservation of emergent phenomena in surrogate models, and conclude that their combination with interpretable machine learning is an effective way to explain the dynamics of complex sociotechnical systems.