Probabilistic Multi-Agent Aircraft Landing Time Prediction

2025-12-09

AI Summary

Predicting aircraft landing times faces dual challenges: trajectory uncertainty and dynamic air traffic control (ATC) interventions—such as radar vectoring—that induce complex inter-aircraft dependencies. Existing models struggle to jointly achieve high prediction accuracy, rigorous uncertainty quantification, and faithful modeling of ATC-driven interactions. To address this, we propose an attention-based multi-agent probabilistic forecasting framework that explicitly captures time-varying, intervention-mediated interactions among aircraft and outputs landing-time predictions as full probability distributions. Our method integrates deep learning with probabilistic graphical modeling to jointly learn trajectory dynamics and quantify epistemic and aleatoric uncertainties from real-world radar surveillance data. Evaluated on operational surveillance data from Incheon International Airport, the model achieves statistically significant improvements in prediction accuracy over state-of-the-art baselines while providing well-calibrated, interpretable uncertainty estimates. This enhances the reliability, transparency, and decision-support capability of modern air traffic management systems.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate and reliable aircraft landing time prediction is essential for effective resource allocation in air traffic management. However, the inherent uncertainty of aircraft trajectories and traffic flows poses significant challenges to both prediction accuracy and trustworthiness. Therefore, prediction models should not only provide point estimates of aircraft landing times but also the uncertainties associated with these predictions. Furthermore, aircraft trajectories are frequently influenced by the presence of nearby aircraft through air traffic control interventions such as radar vectoring. Consequently, landing time prediction models must account for multi-agent interactions in the airspace. In this work, we propose a probabilistic multi-agent aircraft landing time prediction framework that provides the landing times of multiple aircraft as distributions. We evaluate the proposed framework using an air traffic surveillance dataset collected from the terminal airspace of the Incheon International Airport in South Korea. The results demonstrate that the proposed model achieves higher prediction accuracy than the baselines and quantifies the associated uncertainties of its outcomes. In addition, the model uncovered underlying patterns in air traffic control through its attention scores, thereby enhancing explainability.

Problem

• Predict aircraft landing times with uncertainty quantification
• Model multi-agent interactions affecting aircraft trajectories
• Enhance prediction accuracy and explainability in air traffic management

Innovation

• Probabilistic framework predicts landing times as distributions
• Multi-agent interactions modeled using attention mechanisms
• Uncertainty quantification enhances prediction reliability and explainability