33th Congress of the International Council of the Aeronautical Sciences

09 - Air Transport System Efficiency

APPLYING MACHINE LEARNING TO TAXI-TIME PREDICTION ATTOKYO INTERNATIONAL AIRPORT

F. Kato¹, E. Itoh¹; ¹The University of Tokyo, Japan

This study proposes a methodology to apply Machine Learning (ML) methods as possible alternatives to accurately predict taxi-time of departure aircraft from Tokyo International Airport. The experiment demonstrated that random forest regression was able to predict the taxi time with the mean error of about 80 seconds, which is much more accurate than the result of a previous study.


View Paper