Application of data mining, real-time monitoring and visualisation techniques to allow prediction and mitigation of risks in flights before safety events occur (proactive safety management).
This project focused on integration of data from different sources (airport and airline data) and from different databases (safety-related data and operational data) in order to identify robust predictors of outcome variables by applying advanced analytics and visualisation techniques. The aim of the project is to contribute to stakeholders’ capacity to intervene proactively on predicted risks by providing a technology solution that supports the identification and implementation of automatic notification barriers to alert operators of impending safety threats.
We delivered the pattern matching and performance management components of our state of the art safety management system that provides functionality for data collection, real-time data processing, visualisation, notification and alerting to inform crews, flight planners and other decision makers about increased levels of risk before a flight takes off.
The solution included the following features:
The Corballis Pattern Matching module was used to configure bird strike risk patterns, and was able to monitor airport and airline data in order to identify those patterns. Notifications about identified patterns were generated and distributed automatically to relevant stakeholders, i.e. to crews for whose flights an increased risk of bird strike had been identified. This increased the crews’ situational awareness of the most relevant hazards at any given time.