Variable Taxi-Out Time Prediction Based on Machine Learning with Interpretable Attributes

Abstract

This paper presents a machine learning-based approach for predicting the taxi-out time, with the departure process decomposed into two components – the time taken to travel from the gate to the departure queue, and the time spent in the departure queue. Gradient-Boosted Decision Tree (GBDT) models are trained to predict the two components using different feature sets, and a comparison of both model shows that they can provide better prediction accuracy compared with conventional methods, with a Root Mean Squared Error (RMSE) of 1.79 minutes and 0.92 minutes when predicting the taxiing and queuing times respectively, and 78% and 96% of predictions falling within a ±2 minute error margin. Predictions from the GBDT model are analysed and interpreted using SHAP (SHapley Additive exPlanations) values. In particular, the taxiing model identified route features as being the most important feature group, while the queuing model identifies runway queuing features as the most important group. The model explainability provides a pathway towards the certification of machine learning techniques in Air Traffic Controller (ATCO) decision support tools. Finally, a prototype dashboard is presented, providing a visual interface for ATCOs to interpret the model outputs, plan the departure sequence, as well as to analyse the causes of airport delays.