What question did this study set out to answer?

The study aims to develop an edge-based Graph Neural Network (GNN) for accurate network delay prediction in air traffic management.

February 12, 2026AerospaceOpen Access

Edge-Based GNN for Network Delay Prediction Enhanced by Flight Connectivity

View Full Paper

Ask AI

Bookmark

Authors

Novel edge-based GNN predicts network delay in air traffic, indicating improved accuracy for hub airports.

The study aims to develop an edge-based Graph Neural Network (GNN) for accurate network delay prediction in air traffic management.
Developed an edge-based GNN model for delay prediction.
Introduced metrics: delay width and delay strength informed by flight connectivity.
Utilized a message-passing mechanism for learning delay dynamics along air routes.
Conducted experiments on real-world datasets to evaluate performance.
Achieved lowest RMSE, MAE, and MSE compared to state-of-the-art models.
Demonstrated improved accuracy at major hub airports and maintained precision at smaller airports.
Revealed effective capturing of delay propagation dynamics across the air traffic network.

Tang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark