Decision Support for Aircraft Taxi Time based on Deep Metric Learning*

As an essential part of a flight life cycle, the surface taxiing process is closely related to the operational efficiency of the airport. Routing and scheduling can be optimized with an accurate prediction of aircraft taxi time in advance, thus improving the ability of refined management of airport surface. However, the past methods merely provide a taxi time predicted by their models, which are of limited help to airport controllers in decision-making. In order to alleviate this problem, this paper proposes to use a deep metric learning (DML) model to learn the similarity between historical operation scenarios based on basic flight properties, surface traffic situation, and airport weather information. For a given reference flight, the taxi time can be reasonably predicted by finding its similar historical scenarios. In this way, the relevant controllers can make flexible decisions at the tactical level. Experimental verification on the historical data of Shanghai Pudong International Airport shows that the deep model can effectively capture the similarity of taxi time between different scenarios. Besides, compared with the classical machine learning prediction models, the proposed model can predict the taxi time more accurately. With similar historical scenarios as the basis for decision support, the implementation and interpretability of Airport Collaborative Decision-Making (A-CDM) system will be enhanced.

[1]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Edmund K. Burke,et al.  A combined statistical approach and ground movement model for improving taxi time estimations at airports , 2013, J. Oper. Res. Soc..

[3]  Kenneth Kuhn,et al.  A methodology for identifying similar days in air traffic flow management initiative planning , 2016 .

[4]  Jun Chen,et al.  Multi-objective fuzzy rule-based prediction and uncertainty quantification of aircraft taxi time , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[6]  Yaping Zhang,et al.  Predicting Taxi-Out Time at Congested Airports with Optimization-Based Support Vector Regression Methods , 2018 .

[7]  Pernilla Ulfvengren,et al.  Preparing for Airport Collaborative Decision Making (A-CDM) implementation: an evaluation and recommendations , 2014, Cognition, Technology & Work.

[8]  Yi Liu,et al.  Incorporating Predictability Into Cost Optimization for Ground Delay Programs , 2016, Transp. Sci..

[9]  Weining Zhang,et al.  A deep learning method for data recovery in sensor networks using effective spatio-temporal correlation data , 2019 .

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

[11]  Sandip Roy,et al.  Forecasting Weather-Impacted Airport Capacities for Flow Contingency Management: Advanced Methods and Integration , 2013 .

[12]  L. Sherry,et al.  Estimating Taxi-out times with a reinforcement learning algorithm , 2008, 2008 IEEE/AIAA 27th Digital Avionics Systems Conference.

[13]  Tom G. Reynolds,et al.  A statistical learning approach to the modeling of aircraft taxi time , 2010, 29th Digital Avionics Systems Conference.

[14]  Edmund K. Burke,et al.  The Airport Ground Movement Problem: Past and Current Research and Future Directions , 2010 .

[15]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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