Seokbin Yoon

Accurate and reliable aircraft landing time prediction is essential for effective resource allocation in air traffic management. However, the inherent uncertainty in aircraft trajectories and traffic flows poses a significant challenge to both prediction models and their trustworthiness. It is therefore critical for models to provide not only point estimates but also uncertainty associated with those predictions. Furthermore, aircraft trajectories are frequently influenced by the presence of nearby aircraft through air traffic control interventions such as radar vectoring. As a result, landing time prediction models must also account for multi-agent interactions in the airspace. In this work, we propose a probabilistic multi-agent aircraft landing time prediction framework that models the landing times of multiple aircraft as distributions, explicitly capturing the inherent uncertainty. We evaluate our framework using an air traffic surveillance dataset collected from the terminal airspace of Incheon International Airport in South Korea. The results demonstrate that our model achieves higher prediction accuracy while also quantifying the associated uncertainty. In addition, we find that the model uncovers underlying patterns in air traffic control through its attention scores, thereby enhancing explainability.

Flight trajectory prediction for multiple aircraft is essential and provides critical insights into how aircraft navigate within current air traffic flows. However, predicting multi-agent flight trajectories is inherently challenging. One of the major difficulties is modeling both the individual aircraft behaviors over time and the complex interactions between flights. Generating explainable prediction outcomes is also a challenge. Therefore, we propose a Multi-Agent Inverted Transformer, MAIFormer, as a novel neural architecture that predicts multi-agent flight trajectories. The proposed framework features two key attention modules: (i) masked multivariate attention, which captures spatio-temporal patterns of individual aircraft, and (ii) agent attention, which models the social patterns among multiple agents in complex air traffic scenes. We evaluated MAIFormer using a real-world automatic dependent surveillance-broadcast flight trajectory dataset from the terminal airspace of Incheon International Airport in South Korea. The experimental results show that MAIFormer achieves the best performance across multiple metrics and outperforms other methods. In addition, MAIFormer produces prediction outcomes that are interpretable from a human perspective, which improves both the transparency of the model and its practical utility in air traffic control.

Understanding how air traffic controllers construct a mental ’picture’ of complex air traffic situations is crucial but remains a challenge due to the inherently intricate, high-dimensional interactions between aircraft, pilots, and controllers. Previous work on modeling the strategies of air traffic controllers and their mental image of traffic situations often centers on specific air traffic control tasks or pairwise interactions between aircraft, neglecting to capture the comprehensive dynamics of an air traffic situation. To address this issue, we propose a machine learning-based framework for explaining air traffic situations. Specifically, we employ a Transformer-based multi-agent trajectory model that encapsulates both the spatio-temporal movement of aircraft and social interaction between them. By deriving attention scores from the model, we can quantify the influence of individual aircraft on overall traffic dynamics. This provides explainable insights into how air traffic controllers perceive and understand the traffic situation. Trained on real-world air traffic surveillance data collected from the terminal airspace around Incheon International Airport in South Korea, our framework effectively explicates air traffic situations. This could potentially support and enhance the decision-making and situational awareness of air traffic controllers.

Aircraft trajectory modeling plays a crucial role in air traffic management (ATM) and is important for various downstream tasks, including conflict detection and landing time prediction. Dataset augmentation by adding synthetically generated trajectory data is necessary to develop a more robust aircraft trajectory model and ensure that the trajectory dataset is sufficient and balanced. We propose a novel framework called ATRADA for aircraft trajectory dataset augmentation. In the proposed framework, a Transformer encoder learns the underlying patterns in the original trajectory dataset and converts each data point into a context vector in the learned latent space. The converted dataset is projected to reduced dimensions using principal component analysis (PCA), and a Gaussian mixture model (GMM) is applied to fit the probability distribution of the data points in the reduced-dimensional space. Finally, new samples are drawn from the fitted GMM, the dimension of the samples is reverted to the original dimension, and the samples are decoded with a multi-layer perceptron (MLP). Several experiments demonstrate that the framework effectively generates new, high-quality synthetic aircraft trajectory data, which were compared to the results of several baselines.

Aircraft trajectory prediction plays a crucial role in air traffic management and significantly enhances operational safety and efficiency. In this work, we propose an aircraft trajectory prediction model that utilizes an Inverted Transformer, which is a state-of-the-art model for time-series prediction. In a vanilla Transformer, temporal tokens containing the multivariate features are embedded for each time step, but in the Inverted Transformer, each series is embedded independently into variate tokens. The Inverted Transformer captures multivariate correlations in a trajectory sequence, resulting in improved prediction accuracy. The proposed model was validated with actual air traffic surveillance data from the terminal airspace of Incheon International Airport, South Korea. The experimental results demonstrate that the prediction accuracy from the proposed model is superior to those of other deep learning-based prediction models.