Predicting the estimated time of arrival (ETA) plays an essential role in decision support (conflict detection, arrival sequencing, or trajectory optimization) for air traffic controllers. In this paper, a new multiple stages strategy for ETA prediction is proposed based on radar trajectories, including arrival pattern identification, arrival pattern classification, and flight time estimation. First, an intention-oriented trajectory clustering method is developed based on a new trajectory representation technique. Such a proposed trajectory clustering method can group trajectories into different arrival patterns in an efficient way. Second, an arrival pattern classification model is constructed based on random forest and XGBoost algorithms. Then, a flight time regression model is trained for each arrival pattern by using the XGBoost algorithm. Information on current states, historical states, and traffic situations is considered to build the feature set during these processes. Finally, the arrival operation toward Guangzhou International Airport is chosen as a case study. The results illustrate that the proposed method and feature engineering approach could improve the performance of ETA prediction. The proposed multiple stages strategy is superior to the single-model-based ETA prediction.

Data mining has achieved great success in air traffic management as a technology for learning knowledge from historical data that benefits people. However, data mining can rarely be embedded into the trajectory optimization process since regular optimization algorithms cannot utilize the functional and implicit knowledge extracted from historical data in a general paradigm. To tackle this issue, this research proposes a novel data mining-based trajectory generation method that is compatible with existing optimization algorithms. Firstly, the proposed method generates trajectories by combining various maneuvers learned from operation data instead of reconstructing trajectories with generative models. In such a manner, data mining-based trajectory optimization can be achieved by solving a combinatorial optimization problem. Secondly, the proposed method introduces a majorization–minimization-based adversarial training paradigm to train the generation model with more general loss functions, including non-differentiable flight performance constraints. A case study on Guangzhou Baiyun International Airport was conducted to validate the proposed method. The results illustrate that the trajectory generation model can generate trajectories with high fidelity, diversity, and flyability.

The imbalance between air traffic capacity and demand, especially in the terminal maneuvering area, constrains the development of the civil aviation industry. To enhance the capacity, providing aircraft with optimal trajectories is the way forward. The key challenge of building a trajectory optimization model lies in embedding air traffic controllers’ operation experience into the optimization process. Previous efforts proposed a data-driven trajectory optimization method to learn operation experience from historical data for trajectory optimization use, which is limited by the issues of insufficient quantity and diversity of trajectory data. To solve those issues, an improved model is proposed to further improve the trajectory optimization performance. Firstly, this paper exploited a connecting-based trajectory generation model to generate massive synthetic trajectories. Then, this paper used a data-mining-based valuable trajectory identification technique to find valuable trajectories that can be used to enrich its operation experience. A case study on Guangzhou Baiyun International Airport was conducted to verify the proposed method. The results show that the proposed model successfully incorporates more operation experience during the optimization process. Compared with the benchmark model, the proposed model can adapt to more complex air traffic and provide optimal trajectories for more incoming aircraft.

Trajectory optimization is essential for realizing trajectory-based operation and has become a hot topic in air traffic management research in recent years. Although existing optimization models have significantly succeeded in their applications, most still need controllers to intervene during rush hours. To further improve the trajectory optimization performance, this paper proposed a data-driven-based trajectory optimization model that learns human controllers’ experience from historical data and embeds this knowledge into the trajectory optimization model to enhance its performance. Case studies at Guangzhou Baiyun International Airport are conducted to validate the proposed model. Compared with a conventional genetic-algorithm-based trajectory optimization model, the proposed approach—by incorporating real historical trajectory data—demonstrates significantly improved performance in managing arrival flows during peak hours, increasing airspace capacity by approximately 30% under trajectory-based operation conditions. Besides, the optimized trajectories embedded with more actual operation experience are familiar to controllers and pilots; therefore, the airspace user training cost would be relatively low.