A Machine Learning Application for Predicting and Alerting Missed Approaches for Airport Management

This study applied machine learning technique to predict the occurrences of Missed Approach (MA) at an airport. In general, MA events are rare, and they typically occur at an aircraft's descending phase a few minutes before landing. The occurrence of MA is usually indicative of safety-related concerns; however, it may cause excessive delays due to disrupting the arrival sequence during peak hours. This study focused on Denver International Airport (DEN) since MA events occurred more frequently as compared with other airports. Instead of using on-board data of individual aircraft, which is difficult to obtain systematically in real time, this study relied on airport operational data and developed a machine learning model to predict the likelihood of MA occurrences for DEN. The results of this study can inform the design and development of a real-time alerting tool for terminal or tower air traffic managers to take pre-emptive actions for mitigating the impact on terminal efficiency and increasing airport throughput. Lessons learned through this study can be applied to other airports with MA concerns.