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.

预测预计到达时间 (ETA) 在空中交通管制员的决策支持（冲突检测、到达排序或轨迹优化）中起着至关重要的作用。在本文中，提出了一种新的基于雷达轨迹的 ETA 预测多阶段策略，包括到达模式识别、到达模式分类和飞行时间估计。首先，基于新的轨迹表示技术开发了一种面向意图的轨迹聚类方法。这种提出的轨迹聚类方法可以有效地将轨迹分组为不同的到达模式。其次，基于随机森林和XGBoost算法构建到达模式分类模型。然后，使用 XGBoost 算法为每个到达模式训练飞行时间回归模型。当前状态、历史状态和交通状况的信息被认为是在这些过程中构建特征集。最后，选择广州国际机场的进港运行作为案例研究。结果表明，所提出的方法和特征工程方法可以提高 ETA 预测的性能。所提出的多阶段策略优于基于单模型的 ETA 预测。