Democratizing business intelligence and machine learning for air traffic management safety

Resurgent interest in artificial intelligence (AI) techniques focused research attention on their application in aviation systems including air traffic management (ATM), air traffic flow management (ATFM), and unmanned aerial systems traffic management (UTM). By considering a novel cognitive human–machine interface (HMI), configured via machine learning, we examined the requirements for such techniques to be deployed operationally in an ATM system, exploring aspects of vendor verification, regulatory certification, and end-user acceptance. We conclude that research into related fields such as explainable AI (XAI) and computer-aided verification needs to keep pace with applied AI research in order to close the research gaps that could hinder operational deployment. Furthermore, we postulate that the increasing levels of automation and autonomy introduced by AI techniques will eventually subject ATM systems to certification requirements, and we propose a means by which ground-based ATM systems can be accommodated into the existing certification framework for aviation systems.

Download Full-text

Lessons Learned in the Application of Machine Learning Techniques to Air Traffic Management

AIAA AVIATION 2020 FORUM ◽

10.2514/6.2020-2882 ◽

2020 ◽

Author(s):

Banavar Sridhar ◽

Gano Broto Chatterji ◽

Antony D. Evans

Keyword(s):

Machine Learning ◽

Traffic Management ◽

Air Traffic Management ◽

Air Traffic ◽

Lessons Learned ◽

Machine Learning Techniques ◽

Learning Techniques

Download Full-text

Explanation of Machine-Learning Solutions in Air-Traffic Management

Aerospace ◽

10.3390/aerospace8080224 ◽

2021 ◽

Vol 8 (8) ◽

pp. 224

Author(s):

Yibing Xie ◽

Nichakorn Pongsakornsathien ◽

Alessandro Gardi ◽

Roberto Sabatini

Keyword(s):

Machine Learning ◽

Risk Prediction ◽

Traffic Control ◽

Traffic Management ◽

Operational Risk ◽

Air Traffic Management ◽

Air Traffic ◽

Viable Solution ◽

Human Operators ◽

Post Hoc

Advances in the trusted autonomy of air-traffic management (ATM) systems are currently being pursued to cope with the predicted growth in air-traffic densities in all classes of airspace. Highly automated ATM systems relying on artificial intelligence (AI) algorithms for anomaly detection, pattern identification, accurate inference, and optimal conflict resolution are technically feasible and demonstrably able to take on a wide variety of tasks currently accomplished by humans. However, the opaqueness and inexplicability of most intelligent algorithms restrict the usability of such technology. Consequently, AI-based ATM decision-support systems (DSS) are foreseen to integrate eXplainable AI (XAI) in order to increase interpretability and transparency of the system reasoning and, consequently, build the human operators’ trust in these systems. This research presents a viable solution to implement XAI in ATM DSS, providing explanations that can be appraised and analysed by the human air-traffic control operator (ATCO). The maturity of XAI approaches and their application in ATM operational risk prediction is investigated in this paper, which can support both existing ATM advisory services in uncontrolled airspace (Classes E and F) and also drive the inflation of avoidance volumes in emerging performance-driven autonomy concepts. In particular, aviation occurrences and meteorological databases are exploited to train a machine learning (ML)-based risk-prediction tool capable of real-time situation analysis and operational risk monitoring. The proposed approach is based on the XGBoost library, which is a gradient-boost decision tree algorithm for which post-hoc explanations are produced by SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME). Results are presented and discussed, and considerations are made on the most promising strategies for evolving the human–machine interactions (HMI) to strengthen the mutual trust between ATCO and systems. The presented approach is not limited only to conventional applications but also suitable for UAS-traffic management (UTM) and other emerging applications.

Download Full-text

Safety Culture and Safety-Relevant Behavior in Air Traffic Management

Aviation Psychology and Applied Human Factors ◽

10.1027/2192-0923/a000068 ◽

2015 ◽

Vol 5 (1) ◽

pp. 3-17 ◽

Cited By ~ 5

Author(s):

Michaela Schwarz ◽

K. Wolfgang Kallus

Keyword(s):

Safety Culture ◽

Traffic Management ◽

Service Providers ◽

Five Factor Model ◽

Principal Component ◽

Air Traffic Management ◽

Air Traffic ◽

Psychometric Validation ◽

Safety Attitudes ◽

Culture Development

Since 2010, air navigation service providers have been mandated to implement a positive and proactive safety culture based on shared beliefs, assumptions, and values regarding safety. This mandate raised the need to develop and validate a concept and tools to assess the level of safety culture in organizations. An initial set of 40 safety culture questions based on eight themes underwent psychometric validation. Principal component analysis was applied to data from 282 air traffic management staff, producing a five-factor model of informed culture, reporting and learning culture, just culture, and flexible culture, as well as management’s safety attitudes. This five-factor solution was validated across two different occupational groups and assessment dates (construct validity). Criterion validity was partly achieved by predicting safety-relevant behavior on the job through three out of five safety culture scores. Results indicated a nonlinear relationship with safety culture scales. Overall the proposed concept proved reliable and valid with respect to safety culture development, providing a robust foundation for managers, safety experts, and operational and safety researchers to measure and further improve the level of safety culture within the air traffic management context.

Download Full-text