Early Detection of Night Curfew Infringements by Delay Propagation with Neural Networks

Airport night curfews are restrictions applied at some airports that prohibit operations during certain hours of the night, aiming to reduce noise nuisance in the surrounding neighborhood. Despite effectively reducing noise exposure for local residents, these environmental measures can have negative economic and operational effects on the airspace user and the airport, as well as a negative experience for the passenger. This paper presents a model that, for each flight and well before the starting time of the curfew period, is able to provide the probability (risk) of night curfew infringement. The risk of night curfew infringement is computed from the start time of the restriction and the distribution of in-block times. The former is known for each airport, while the latter is provided by a neural network which was trained on historical data to predict the propagation of arrival delay along the sequence of flights of an aircraft. Results show that the model significantly improves the in-block time predictions, if compared to the current solution. Furthermore, the risk indicator could assist in identifying flights with potential risk of night curfew infringements within a reasonable time frame to implement effective mitigation actions.