Multifactor Model for Predicting Delays at U.S. Airports

Abstract

Traffic flow management (TFM), in coordination with airline operation centers, manages the arrival and departure flow of aircraft at the nation's airports on the basis of airport arrival and departure rates for each 15-min segment throughout the day. The management of traffic flow has become so efficient in the United States that approximately 95% of delays now occur at the airports (not while airborne). Inefficiencies in traffic flow occur when nontraffic flow delays (e.g., carrier, turnaround, aircraft swapping, and local weather delays) are superimposed on the traffic flow delays. Researchers have correlated these nontraffic flow delays at airports with sets of causal factors and have created models to predict aggregate delays at airports on the time scale of a day. To be consistent with the way traffic flow is managed, a model of causal factors of delays in 15-min increments would provide the basis for improving the efficiency of TFM. The development of multifactor models for predicting airport delays in 15-min epochs at 34 operational evolution plan airports is described. The models are created by using multivariate adaptive regression splines. The models, generated by using historic individual airport data, exhibit an accuracy of 5.3 min for generated delay across all airports and 2.1 min for absorbed delay across all airports. A summary of the factors that drive the performance of each airport is provided. The implications of these results are discussed.