Xinglong Wang

The aircraft landing problem (ALP) poses significant challenges for traditional Monte Carlo Tree Search (MCTS) due to its vast search space and reliance on inefficient random simulations. To overcome these limitations, this paper proposes a novel Transformer-Augmented Monte Carlo Tree Search (TMCTS) algorithm. Our approach integrates a reinforcement learning framework that incorporates key operational constraints, including wake turbulence separation and time windows, and employs a cost function aimed at minimizing both delay time and fuel consumption. A core innovation is the replacement of the conventional random simulation phase in MCTS with a Transformer-based value predictor. This leverages the Transformer’s superior ability to model sequences and capture global dependencies among flights, thereby dramatically accelerating search convergence. Specifically, we designed a two-head Transformer network (comprising policy and value heads) to provide informed prior knowledge, which effectively guides the selection and expansion steps of the MCTS tree. The model is trained within an Actor–Critic framework, utilizing behavior cloning for pre-training followed by reinforcement learning for fine-tuning. Experimental evaluations on the standard OR-Library benchmark demonstrate that our TMCTS method significantly reduces scheduling deviation compared to state-of-the-art baselines (including FCFS, DPALO+GA, DPALO+PSO, and CPLEX). Moreover, it achieves a 93.7% reduction in computation time relative to the CPLEX method, highlighting its superior efficiency and practical applicability for real-time scheduling.

The Aircraft Landing Problem (ALP) poses significant challenges for traditional Monte Carlo Tree Search (MCTS) due to its vast search space and reliance on inefficient random simulations. To overcome these limitations, this paper proposes a novel Transformer-Augmented Monte Carlo Tree Search (TMCTS) algorithm. Our approach integrates a reinforcement learning framework that incorporates key operational constraints, including wake turbulence separation and time windows, and employs a cost function aimed at minimizing both delay time and fuel consumption. A core innovation is the replacement of the conventional random simulation phase in MCTS with a Transformer-based value predictor. This leverages the Transformer’s superior capability in sequence modeling and capturing global dependencies among flights, thereby dramatically accelerating search convergence. Specifically, we design a two-head Transformer network (comprising policy and value heads) to provide informed prior knowledge, which effectively guides the selection and expansion steps of the MCTS tree. The model is trained within an Actor-Critic framework, utilizing behavior cloning for pre-training followed by reinforcement learning for fine-tuning. Experimental evaluations on the standard OR-Library benchmark demonstrate that our TMCTS method significantly reduces scheduling deviation compared to state-of-the-art baselines (including DPALO+GA, DPALO+PSO, and DALP). Moreover, it achieves a 90.6% reduction in computation time relative to the DALP method, highlighting its superior efficiency and practical applicability for real-time scheduling.

With the continuous increase of China’s air traffic volume, the number of aircraft and support vehicles in the airfield area is increasing. In view of the increasingly complex surface traffic situation, the risk of conflict in the airfield area is increasing. In this paper, first, taking the large moving targets in the airfield as the network nodes and the potential conflict relationship between the targets as the connecting edge, the network model of the moving targets in the airfield is constructed. On this basis, the community structure detection algorithm is used to detect the active target community in the flight area, and the K ‐means clustering algorithm is used to divide the risk level of the network in time according to the state characteristics of the cluster, so as to identify the high‐risk moments in the airfield area. Finally, for the three indicators of node selection degree, point strength and weighted clustering coefficient at high‐risk time, the combination weighting method is used to identify the potential conflict of nodes and accurately identify high‐risk nodes in space. Finally, taking Xi’an Xianyang Airport as an example, the experimental results show that the conflict classification and risk identification method proposed in this paper can accurately identify the conflict risk in the flight area in time and space.

The siphon effect between airports has amplified the polarization in passenger throughput, undermining the balanced development and sustainability of airport clusters. The airport siphon effect occurs when one airport attracts a disproportionate share of passengers, concentrating traffic at the expense of others, which affects the overall resilience of the entire airport cluster. To address this issue, this study proposes a siphon index, expands the range of ground transportation options for passengers, and establishes a zero-siphon model to assess the impact of siphoning on the resiliency of airport clusters. Using this framework, four major airport clusters in China were selected as research subjects, with regional aviation accessibility serving as a measure of resilience. The results showed that among the four airport clusters, the siphon effect is most pronounced in the Guangzhou region. To explore the implications of this effect further, three airport disruption scenarios were simulated to assess the resilience of the Pearl River Delta airport cluster. The results indicated that the intensity and timing of disruptive events significantly affect airport cluster resilience, with hub airports being particularly sensitive. This study analyzes the risks associated with excessive route concentration, providing policymakers with critical insights to enhance the sustainability, equity, and resilience of airport clusters. The proposed strategies facilitate coordinated infrastructure development, optimized air–ground intermodal connectivity, and risk mitigation. These measures contribute to building more sustainable and adaptive aviation networks in rapidly urbanizing regions.

Airspace sectorization is an effective approach to balance increasing air traffic demand and limited airspace resources. It directly impacts the efficiency and safety of airspace operations. Traditional airspace sectorization methods are often based on fixed spatial scales, failing to fully consider the complexity and interrelationships of airspace partitioning across different spatial scales. This makes it challenging to balance large-scale airspace management with local dynamic demands. To address this issue, a multi-scale airspace sectorization framework is proposed, which integrates a multi-resolution grid system and a hierarchical deep reinforcement learning algorithm. First, an airspace grid model is constructed using Quaternary Triangular Mesh (QTM), along with an efficient workload calculation model based on grid encoding. Then, a sector optimization model is developed using hierarchical deep Q-network (HDQN), where the top-level and bottom-level policies coordinate to perform global airspace control area partitioning and local sectorization. The use of multi-resolution grids enhances the interaction efficiency between the reinforcement learning model and the environment. Prior knowledge is also incorporated to enhance training efficiency and effectiveness. Experimental results demonstrate that the proposed framework outperforms traditional models in both computational efficiency and workload balancing performance.

To ensure the safety of operations in the airfield area, it is crucial to address the increased conflict risks resulting from the growing number of vehicles and aircraft. Based on the complex network theory, this study takes aircraft and vehicles in the airfield area as nodes and selects five different indicators (average degree, average node weight, average weighted clustering coefficient, network density, and network efficiency) to characterize the operation state of the airfield area, so as to identify conflict risks. Building on this framework, an ATT‐Bi‐LSTM innovation prediction model based on LSTM network architecture is established to forecast the evolution of network indicators over time. By leveraging the algorithm to predict the temporal evolution of indicators, valuable insights into the future evolution of conflict risk can be gleaned from the prediction results. Real operational data from Xi’an Xianyang Airport are utilized as a demonstrative example in this study. The results of the experiments illustrate that the analytical approach proposed in this study achieves a precise identification of the indicators. The experimental results are then compared with data from other predictive models that operate on the same data set. Compared to alternative prediction models, the accuracy is increased by nearly 10%, reaching 89.78%. The results of the study help to accurately identify conflict risks in the airfield area in advance and provide strategic conflict avoidance strategies for relevant staff. This is essential to ensure the security of airfield area.

The increased number of severe weather events caused by global warming in recent years is a major turbulence factor for airport operation and results in more irregular flights. Quantifying the system response status towards turbulence is critical, in order for airports to deal with severe weather. For this reason, we propose a resilience framework that is in compliance with resilience theory to evaluate airport flight operations. In this framework, the departure rate (DPR), normal weather baseline (NWB), and nonnegative general resilience (NGR) were defined and used. Meanwhile, the whole process is divided into five phases before and after disturbance, and the system capacities of susceptibility, absorption, adaptation, and recovery are assessed. In order to clarify the performance of the framework towards various severe weather conditions, an analysis was conducted at Beijing Capital Airport in China based on a dataset that includes both the meteorological terminal aviation weather report (METAR) and flight operations from January to July 2021. The results show that the newly proposed resilience framework can commendably reflect airport flight operation performance. The airport flight operation resilience characteristic is different with severe weather. Compared to sandstorms and snow, airport flight operation with stronger robustness was observed during thunderstorm events. The study also confirms that, as the weather warning level increases, the disruption time increases and response time decreases accordingly. The above results could assist researchers and policy makers in clearly understanding the real-world resilience of airport flight operation, in both theory and practice, and responding to emergent disruptive events effectively.