Anomaly Detection in National Airspace System (NAS) 

[2017 - 2019] 

The air traffic system is one of the most complex and safety-critical systems, which is expected to grow at an average rate of 0.9% a year in its operational activities within the National Airspace System. In such systems, it is important to identify degradations in system performance, especially in terms of safety and efficiency. Among the operations of various subsystems of the air traffic system, the arrival and departure operations in the terminal airspace require more attention because of its higher impact (about 75% incidents) on the entire system’s safety, ranging from single aircraft incidents to multi-airport congestion incidents. 

Our goal is to identify the air traffic system’s degradations, called anomalies, in the multi-airport terminal airspace, or metroplex airspace, by developing anomaly detection models that can separate anomalous flights from normal ones. Within the metroplex airspace, airport operational parameters such as runway configuration and coordination between proximal airports are a major driving factor in aircraft’s behaviors. As a substantial amount of data is continually recording such behaviors through sensing technologies and data collection capabilities, modern machine learning techniques provide powerful tools for the identification of anomalous flights in the metroplex airspace. 

The proposed algorithm ingests heterogeneous data, comprising the surveillance data, which represents an aircraft’s physical behaviors, and the airport operations data, which reflects operational procedures at airports. Typically, such aviation data is unlabeled, and thus the proposed algorithm is developed based on hierarchical unsupervised learning approaches for anomaly detection. This base algorithm has been extended in a two-fold manner: 

1.  an anomaly monitoring algorithm which uses the developed anomaly detection models to detect anomalous flights within real-time streaming data; and 

2. a precursor detection algorithm which learns the causes for the detected anomalies using supervised learning approaches.

 The proposed algorithms are demonstrated with real aviation data recorded in the New York metroplex, and the results show that the proposed algorithms have a potential to be used as decision-support tools that can aid pilots and air traffic controllers to mitigate anomalies from ever occurring, thus improving the safety and efficiency of the metroplex airspace operations.

Principal Investigators

• Kwangyeon Kim 

• Raj Deshmukh

• Daiwei Sun

Related Publications

• "Terminal Airspace Anomaly Detection Using Temporal Logic Learning", K. Kim and I. Hwang, ICRAT 2018, Barcelona, Spain

• "Anomaly Detection Using Temporal Logic Based Learning for Terminal Airspace Operations", R. Deshmukh and I. Hwang, AIAA SciTech 2019, San Diego, California

• "Incremental-Learning-Based Unsupervised Anomaly Detection Algorithm for Terminal Airspace Operations", R. Deshmukh and I. Hwang,  AIAA Journal of Aerospace Information Systems, 2019

• "Data-Driven Precursor Detection Algorithm for Terminal Airspace Operations", R. Deshmukh, D. Sun and I. Hwang, ATM Seminar 2019, Vienna, Austria, June 2019 

• "Learning-based Anomaly Detection in Metroplex Terminal Airspace Operations", R. Deshmukh, D. Sun, K. Kim and I. Hwang, Transportation Research Part C: Emerging Technologies, submitted (Dec 2019)

Sponsors

N/A