Can machines learn how to forecast taxi-out time? A comparison of predictive models applied to the case of Seattle/Tacoma International Airport

This study compares the performance of ensemble machine learning, ordinary least-squared and penalized algorithms to predict taxi-out time at two different periods of NextGen capability implementation. In the pre-sample, ordinary least-squared and ridge models performed better than other ensemble learning models. However, the gradient boosting model provided the lowest root mean squared errors in the post-sample. No algorithm fits data better in all cases. This paper recommends selecting the model that provides the best balance between bias and variance.

[1]  Alberto Boschetti,et al.  Regression Analysis with Python , 2016 .

[2]  Peter Bühlmann,et al.  Bagging, Boosting and Ensemble Methods , 2012 .

[3]  Tom Reynolds,et al.  Airport systems planning, design, and management , 2003 .

[4]  Cha Zhang,et al.  Ensemble Machine Learning: Methods and Applications , 2012 .

[5]  Edmund K. Burke,et al.  Aircraft taxi time prediction: Comparisons and insights , 2014, Appl. Soft Comput..

[6]  C. Sutton.  Classification and Regression Trees, Bagging, and Boosting , 2005 .

[7]  Myung Suk Kim,et al.  Analysis of short-term forecasting for flight arrival time , 2016 .

[8]  Pratap Dangeti,et al.  Statistics for Machine Learning , 2017 .

[9]  Sebastian Raschka,et al.  Python Machine Learning , 2015 .

[10]  Tony Diana.  An application of survival and frailty analysis to the study of taxi-out time: A case of New York Kennedy Airport , 2013 .

[11]  John-Paul Clarke,et al.  Queuing Model for Taxi-Out Time Estimation , 2002 .

[12]  Wolfgang Jank,et al.  Estimating Flight Departure Delay Distributions - A Statistical Approach With Long-Term Trend and Short-Term Pattern , 2008 .

[13]  Dennis C. Dietz,et al.  Modeling and Analysis of an Airport Departure Process , 1997 .

[14]  Lance Sherry,et al.  Multifactor Model for Predicting Delays at U.S. Airports , 2008 .

[15]  Michael Bowles.  Machine Learning in Python: Essential Techniques for Predictive Analysis , 2015 .

[16]  Tony Diana.  Can Delay Propagation be Predicted? A Case Study of the Three Largest New York Area Airports Using Neural Networks , 2010 .

[17]  Robert A. Shumsky.  Real-Time Forecasts of Aircraft Departure Queues , 1997 .

[18]  Nicolas Pujet.  Modeling and control of the departure process of congested airports , 1999 .

[19]  Robert Horonjeff,et al.  Planning and design of airports , 1950 .

[20]  Lance Sherry,et al.  Accuracy of reinforcement learning algorithms for predicting aircraft taxi-out times: A case-study of Tampa Bay departures , 2010 .

[21]  H. Akaike.  A new look at the statistical model identification , 1974 .

[22]  Oriol Lordan,et al.  Forecasting of taxi times: The case of Barcelona-El Prat airport , 2016 .

[23]  Tony Diana,et al.  Mapping the Surface Movement Area Operations: An Application of Petri Nets to the Case of New York JFK Airport , 2012 .

[24]  Vinayak Deshpande,et al.  The Impact of Airline Flight Schedules on Flight Delays , 2012, Manuf. Serv. Oper. Manag..