Airport Taxi Time Prediction and Alerting: A Convolutional Neural Network Approach

TL;DR

This paper introduces a convolutional neural network model that predicts whether airport taxi-out times will exceed a threshold within the next hour, using surface radar data for automatic inference of operational conditions.

Contribution

It presents a novel computer vision-based approach that learns from radar data to predict taxi times without extensive modeling of individual taxiing activities.

Findings

Effective prediction of taxi-out time exceedance within an hour

Utilizes minimal processing of radar data for surface information

Automatically infers operational conditions like runway configuration

Abstract

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).