Data-Driven Methods for Aviation Safety: From Data to Knowledge

Abstract

Demand upon the future Air Traffic Management (ATM) systems is expected to grow to possibly exceed available system capacity, pushing forward the need for automation and digitisation to maintain safety while increasing efficiency. This work focuses on a manifestation of ATM safety, the Loss of Separation (LoS), exploiting safety reports and ATM-system data (e.g., flights information, radar tracks, and Air Traffic Control events). Current research on Data-Driven Models (DDMs) is rarely able to support safety practitioners in the process of investigation of an incident after it happened. Furthermore, integration between different sources of data (i.e., free-text reports and structured ATM data) is almost never exploited.To fill these gaps, the authors propose (i) to automatically extract information from Safety Reports and (ii) to develop a DDM able to automatically assess if the Pilots or the Air Traffic Controller (ATCo) or both contributed to the incident, as soon as the LoS happens. The LoSs' reported in the public database of the

Machine Learning-based Aircraft Conflict Prediction: A Systematic Literature Review

“…The authors in [16] proposed an approach which extracts data from aircraft Safety Reports automatically which is given as input to the Data-Driven Model that predicts whether pilot air traffic controller or both contributes in an incident when loss of separation occurs.…”