Towards Situation-aware State Modeling for Air Traffic Flow Prediction

2026-04-13

AI Summary

This work addresses the limitations of existing data-driven approaches in terminal airspace traffic prediction, which often neglect aircraft real-time kinematic states and their distances to airspace boundaries, thereby constraining predictive accuracy. To overcome this, the authors propose AeroSense, a novel framework that pioneers a modeling paradigm directly incorporating microscopic aircraft states as input, representing the airspace situation as a dynamic set of states. AeroSense introduces context-aware state representations and a masked self-attention mechanism to capture inter-aircraft interactions, complemented by a dual-decoupled prediction head and a multi-objective optimization strategy. Evaluated on large-scale real-world airport datasets, AeroSense significantly outperforms time-series baselines, demonstrating robust performance during peak traffic periods and enhanced interpretability through attention visualization.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose \textit{AeroSense}, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as \textit{a dynamic set of aircraft states}, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through attention-based visualizations.

Problem

• air traffic flow prediction
• terminal airspace
• aircraft state modeling
• situation awareness
• time series forecasting

Innovation

• state-to-flow modeling
• situation-aware representation
• masked self-attention
• microscopic aircraft states
• heterogeneous flow dynamics