Airport Taxi Time Prediction and Alerting: A Convolutional Neural Network Approach
This addresses operational efficiency for airport management by providing timely alerts, though it is incremental as it builds on prior flight-by-flight prediction methods.
The paper tackles the problem of predicting whether average airport taxi-out times will exceed a threshold within the next hour, using a novel computer vision-based model that learns directly from surface radar data, achieving implicit inference of airport-specific information without extensive manual modeling.
This paper proposes a novel approach to predict and determine whether the average taxi- out time at an airport will exceed a pre-defined threshold within the next hour of operations. Prior work in this domain has focused exclusively on predicting taxi-out times on a flight-by-flight basis, which requires significant efforts and data on modeling taxiing activities from gates to runways. Learning directly from surface radar information with minimal processing, a computer vision-based model is proposed that incorporates airport surface data in such a way that adaptation-specific information (e.g., runway configuration, the state of aircraft in the taxiing process) is inferred implicitly and automatically by Artificial Intelligence (AI).