Abstract

The predicted growth in air transportation and the ambitious goal of the European Commission to have on-time performance of flights within 1 minute, makes efficient and predictable ground operations at airports indispensable.
Accurately predicting taxi times of arrivals and departures serves as an important key task for runway sequencing, gate
assignment and ground movement itself. This research tests different regression approaches to more accurately predict
taxi times. Historic data from two major European airports is utilised for cross-validation. Detailed comparisons show
that a TSK fuzzy rule-based system outperformed the other approaches in terms of prediction accuracy. Insights from
this approach are then presented, focusing on the analysis of taxi-in times, which is rarely discussed in literature.