Alert systems detect critical events which can happen in the short term. Uncertainties in data and in the models used for detection cause alert errors. In the case of air traffic control systems such as Short-Term Conflict Alert (STCA), uncertainty increases errors in alerts of separation loss. Statistical methods that are based on analytical assumptions can provide biased estimates of uncertainties. More accurate analysis can be achieved by using Bayesian Model Averaging, which provides estimates of the posterior probability distribution of a prediction. Th project aims to explore new approaches to estimate the prediction uncertainty, based on observations that the uncertainty can be quantified by variance of predicted outcomes. In this approach, predictions for which variances of posterior probabilities are above a given threshold are assigned to be uncertain. A design approach has to be verified within a probabilistic framework based on the extrapolation of the closest point of approach. The project can use available Heathrow airport flight data to demonstrate an improvement in detection accuracy. Achieving a high accuracy of modelling the STCA system is a necessary condition for evaluating the uncertainty in prediction. Comparison with a bootstrap aggregation and other ML techniques is required in order to demonstrate a reduction of uncertainty in predictions.
Research questions: (1) to explore the ability of designed detection strategies to extend the Air Traffic Management (2) to explore ways of designing reliable decision models within the Bayesian framework.
The deadlines are as follows:
For March starters:
International applicants - 30th November 2021
UK nationals - 18th January 2022
For October starters:
International applicants - 30th June 2022
UK nationals - 5th August 2022