Exploring the delay causality between airports and comparing the delay propagation patterns across different airport networks is critical to better understand delay propagation mechanisms and provide effective delay mitigation strategies. A novel attention-based recurrent graph convolutional neural network is proposed to identify the hidden delay causality relationship among airports in three different airport networks of China. The selected three airport networks show great heterogeneities in topological characteristics, such as average intensity, modularity and eigenvector centrality. The modeling results indicate that the identified delay causality networks of three airport networks are greatly varied in terms of complexity, delay propagation distance and efficiency. Moreover, the delay state of each airport is categorized into three levels, and the delay state transition of the three networks is explored. The results indicate that delay state transition in the North China Control Area exhibits an obvious bidirectional transition form that mainly propagates between the large-degree airports and small-degree airports, while severe delays of some hub airports account for a relatively large proportion in the other two networks. The results of this study could better reveal the delay propagation mechanism among airports and help airport operators develop effective strategies to alleviate flight delays and improve airport operation efficiency.

To allocate the en-routes and slots resource to the flights with collaborative decision-making, a multiobjective 0-1 integer programming model was proposed. According to different demands from air traffic control departments, airlines, and passengers, efficiency, equity, and effectiveness principles of collaborative decision-making were considered. With the aim to minimize the total flight delay costs, the total number of turning points, and average delay time of passengers, the effectiveness constraints were achieved. The algorithm was designed to solve the model on the basis of the objective method, and Lingo11 and MatlabR2007b were applied in numerical tests. To test how well the model works in real world, a numerical test was performed based on the simulated data of a civil en-route. Test results show that, compared with the traditional strategy of first come first served, the model gains better effect. The superiority of the model was verified.

To allocate the en-routes and slots to the flights with collaborative decision making, a collaborative en-route and slot allocation algorithm based on fuzzy comprehensive evaluation was proposed. Evaluation indexes include flight delay costs, delay time and the number of turning points. Analytic hierarchy process is applied to determining index weights. Remark set for current two flights not yet obtained the en-route and slot in flight schedule is established. Then, fuzzy comprehensive evaluation is performed, and the en-route and slot for the current two flights are determined. Continue selecting the flight not yet obtained an en-route and a slot in flight schedule. Perform fuzzy comprehensive evaluation until all flights have obtained the en-routes and slots. MatlabR2007b was applied to numerical test based on the simulated data of a civil en-route. Test results show that, compared with the traditional strategy of first come first service, the algorithm gains better effect. The effectiveness of the algorithm was verified.