A Deep Unsupervised Learning Approach for Airspace Complexity Evaluation

Abstract

Airspace complexity is a critical metric in current Air Traffic Management systems for indicating the security degree of airspace operations. Airspace complexity can be affected by many coupling factors in a complicated and nonlinear way, making it extremely difficult to be evaluated. In recent years, machine learning has been proved as a promising approach and achieved significant results in evaluating airspace complexity. However, existing machine learning based approaches require a large number of airspace operational data labeled by experts. Due to the high cost in labeling the operational data and the dynamical nature of the airspace operating environment, such data are often limited and may not be suitable for the changing airspace situation. In light of these, we propose a novel unsupervised learning approach for airspace complexity evaluation based on a deep neural network trained by unlabeled samples. We introduce a new loss function to better address the characteristics pertaining to airspace complexity data, including dimension coupling, category imbalance, and overlapped boundaries. Due to these characteristics, the generalization ability of existing unsupervised models is adversely impacted. The proposed approach is validated through extensive experiments based on the real-world data of six sectors in Southwestern China airspace. Experimental results show that our deep unsupervised model outperforms the state-of-the-art methods in terms of airspace complexity evaluation accuracy.