Air Traffic Controller Task Demand via Graph Neural Networks: An Interpretable Approach to Airspace Complexity

2025-07-17

AI Summary

Addressing the challenge of real-time assessment of short-term taskload on air traffic controllers (ATCOs) and the inability of conventional complexity metrics to capture aircraft-to-aircraft interaction-driven dynamics, this paper proposes an interpretable evaluation framework based on attention-enhanced graph neural networks (GNNs). The method jointly models static airspace topology and dynamic inter-aircraft interactions to predict the number of upcoming control instructions. Through systematic ablation analysis, it quantifies each aircraft’s marginal contribution to overall taskload, yielding interpretable individual demand scores. Compared with traditional heuristic approaches and state-of-the-art complexity metrics, our framework achieves significantly higher accuracy in instruction count prediction and greater reliability in taskload attribution. It thus provides a practical, operationally grounded analytical tool for ATCO training optimization and airspace structure design.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Real-time assessment of near-term Air Traffic Controller (ATCO) task demand is a critical challenge in an increasingly crowded airspace, as existing complexity metrics often fail to capture nuanced operational drivers beyond simple aircraft counts. This work introduces an interpretable Graph Neural Network (GNN) framework to address this gap. Our attention-based model predicts the number of upcoming clearances, the instructions issued to aircraft by ATCOs, from interactions within static traffic scenarios. Crucially, we derive an interpretable, per-aircraft task demand score by systematically ablating aircraft and measuring the impact on the model's predictions. Our framework significantly outperforms an ATCO-inspired heuristic and is a more reliable estimator of scenario complexity than established baselines. The resulting tool can attribute task demand to specific aircraft, offering a new way to analyse and understand the drivers of complexity for applications in controller training and airspace redesign.

Problem

• Predicting real-time Air Traffic Controller task demand
• Interpreting airspace complexity via Graph Neural Networks
• Identifying specific aircraft contributing to task demand

Innovation

• Interpretable Graph Neural Network framework
• Attention-based model predicts upcoming clearances
• Per-aircraft task demand score via ablation