The departure time uncertainty exacerbates the inaccuracy of arrival time estimation and demand for arrival slots, particularly for movements to capacity constrained airports. The Estimated Take-Off Time (ETOT) or Estimated Departure Time(ETD) for each individual flight is currently derived from Air Traffic Flow Management System (ATFMS), which are solely determined based on individual flight plan Estimated Off Block Time(EOBT) or subsequent delays updated by Airline. Even if normal weather conditions prevail, aircraft departure times will differ from ETOTs determined by the ATFMS due to a number of factors such as congestion, early/delayed inbound flight (linked flights), reactionary delays and air traffic flow management slot changes. This paper presents a model that predicts departure time variance based on the previous leg departure time using a combination of exponential moving average and machine learning methods. The model correctly classifies the departure time (Early, On Time, Delay) based on the previous leg departure state, allowing the ATFM system to measure the arrival time of a capacity constrained airport with greater accuracy and better assess demand requirements. The results show that the proposed model with M5P Regression tree provides the best results, with Mean Absolute Error and Root Mean Square Error (RMSE) of 3.43 and 4.83, respectively, indicating a 50% improvement over previous research findings. Whereas, with logistic regression, the classification of departure time (Early, On Time, Delay) is achieved a better accuracy of 91 %, which is higher than previous works.


We would like to thank Airports Authority of India for providing data for the research.