Aircraft taxi time prediction: Comparisons and insights

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 statistical regression approaches and also various regression methods which fall into the realm of soft computing, 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. The aim of this research is to unleash the power of soft computing methods, in particular fuzzy rule-based systems, for taxi time prediction problems, and to show that, although these methods have only been recently applied to airport problems, they present promising and potential features for such problems.

Predicting Taxi-Out Time at Congested Airports with Optimization-Based Support Vector Regression Methods

“…In recent years, researchers have found that departure taxi-out time is related to numerous factors, including the number of departing aircraft in the runway queue, the number of arriving aircraft taxiing, the time of day [2,13], airlines, and taxiing route distance [14,15]. Departure delay is also a significant factor in some specific airports such as PEK.…”

“…Ravizza et al built a combined statistical and ground movement model and used multiple linear regression to find the function that would predict taxiing times more accurately [14]. Also, they used the same explanatory variables for different approaches, which included multiple linear regression, least median squared linear regression, Support Vector Regression, M5 model trees, Mamdani fuzzy rule-based systems, and TSK fuzzy rule-based systems, to predict taxi-out times and then compared these approaches [15]. Lee et al used both fast-time simulation and machine-learning techniques to predict taxi-out time and found the prediction method of Support Vector Regression to be better than the linear regression method and the Dead Reckoning method [16].…”

“…This research aims to compare the swarm intelligence algorithm based SVR methods and other prediction methods, to evaluate performance by using the prediction accuracy measures in statistics as presented in (15) to (18):…”

Taxi Time Prediction at Charlotte Airport Using Fast-Time Simulation and Machine Learning Techniques

“…[13][14][15] Recently, various regression methods, including multiple linear regression, least median squared linear regression, support vector regression, model trees, and fuzzy rule-based systems, were also applied to European airports for taxi time prediction problems. 16,17 In addition to the data-driven approaches above, air traffic simulation tools can be used for validation and performance evaluation of taxi time prediction functions, provided they represent the surface traffic flow at a target airport realistically. Various simulation tools have been developed for modeling and analyzing airport operations in the past decades.…”

Taxi-Out Time Prediction for Departures at Charlotte Airport Using Machine Learning Techniques

“…[12][13][14] Various regression methods, including multiple linear regression, least median squared linear regression, support vector regression, model trees, and fuzzy rule-based systems, were also applied to several airports in Europe for taxi time prediction problems. 15,16 Each machine learning method was independently applied to the limited test data at different airports under different conditions, and therefore the prediction performance varied with the prediction model.…”