Data-Driven Runway and Taxiway Exits Prediction of Landing Aircraft: A Case Study at Hartsfield-Jackson Atlanta International Airport

2026-06-09

AI Summary

This study addresses ground movement efficiency at high-traffic airports by proposing a two-stage, data-driven decision support system. The first stage predicts the runway exit selected by arriving aircraft, while the second stage forecasts whether the aircraft will cross an active departure runway or use an end-around taxiway. The system integrates multi-source data—including ASDE-X trajectories, aircraft characteristics, gate assignments, short-term traffic flow, and weather—into an interpretable and well-calibrated machine learning framework, with XGBoost and LightGBM yielding optimal performance. Designed to preserve air traffic controllers’ ultimate authority, the system enhances situational awareness without automating decisions. Experimental results demonstrate prediction accuracies of 0.86–0.89 for exit selection and 0.70–0.74 for crossing versus end-around decisions, with approach speed emerging as the dominant factor in exit choice, and departure rate and gate location significantly influencing taxi routing behavior.

Abstract

Airport surface operations increasingly constrain performance at high-throughput hubs. This study examines arrival taxi-in decisions at Hartsfield-Jackson Atlanta International Airport (KATL) and proposes a two-stage, data-driven decision aid that mirrors controller workflow. Stage I predicts the runway exit selected by an arriving aircraft. Stage II predicts whether, given that exit, the aircraft will cross the active departure runway at a designated point or use the end-around taxiway. Models are trained using ASDE-X surface trajectories, aircraft characteristics, ramp destinations, short-horizon traffic rates, and weather across multiple look-back windows. We benchmark nine classifiers, including Random Forest, XGBoost, LightGBM, and CatBoost, and evaluate accuracy, macro-F1, precision-recall behavior, confusion matrices, Brier score, and Expected Calibration Error. Across east and west flows, XGBoost and LightGBM outperform Random Forest. Stage I achieves 0.86-0.89 accuracy with macro-F1 scores of 0.40-0.50, while Stage II achieves 0.70-0.74 accuracy with macro-F1 scores of 0.28-0.55. Feature-importance analysis shows that approach speed is the main driver of exit choice. Departure rate, crossing rate, ramp destination, and, for west flow, the selected exit are the strongest predictors of crossing versus end-around routing. Minority classes remain harder to predict because of feature-space overlap, as shown by t-SNE and UMAP analyses. The proposed framework supports controller situational awareness through calibrated, explainable predictions while preserving human responsibility for final routing decisions.

Problem

• runway exit prediction
• taxi-in routing
• airport surface operations
• arrival aircraft
• crossing decision

Innovation

• data-driven prediction
• two-stage modeling
• airport surface operations
• XGBoost/LightGBM
• explainable AI