Transport causality knowledge-guided GCN for propagated delay prediction in airport delay propagation networks

Flight delays pose a worldwide challenge that significantly affect the safety and efficiency of air transportation systems. However, propagated delay prediction, as well as its causality among airport delay propagation net-works, has not considered some crucial issues regarding spatiotemporal dependence and propagation relation-ships. Thus, this study proposes a transport causality knowledge-guided extended graph convolutional network (GCN) framework to tackle these issues. In particular, a causality knowledge-guided airport delay propagation network (ADPN) is developed using the second modified transfer entropy (SMTE) principle. Furthermore, a causality-embedded adjacency matrix is utilized by an extended GCN for propagated delay prediction. Comprehensive validations and results indicate that the proposed method benefits significantly from the cau-sality knowledge, and increases the prediction performances up to 15.51%. Thus, transport causality is signifi-cant and efficient for understanding propagated delay features and airport delay propagation network characteristics.

Automated summary

Flight delays are a worldwide challenge that significantly affects the safety and efficiency of air transportation systems. This study proposes a transport causality knowledge-guided extended graph convolutional network framework to address the crucial issues in propagated delay prediction. By developing a causality knowledge-guided airport delay propagation network and utilizing a causality-embedded adjacency matrix for delay prediction, the proposed method significantly improves the prediction performance.