Safety Assessment of Air Transportation System: A Machine Learning Perspective

Abstract

Safety, as the most important concern in civil aviation, needs to be maintained at an acceptable level in the air transportation system. As we are moving to the Next-Generation (NextGen) air transportation  system, a multitude of new and existing aviation data sources are expected to become available,  such as trajectory data, voice data, weather forecasting, and aircraft health data. 

This talk concentrates on giving an overview on the recent progress of several machine learning models developed for assessing the safety of the air transportation system, where a diverse set of data sources will be exploited. Specifically, multiple safety assessment models developed with state-of-the-art machine learning algorithms, including Bayesian neural network, ensemble models, long-short term memory (LSTM) neural network, and Bayesian network, will be introduced. These models are built with the data from a broad range of sources, such as SWIM Flight Data Publication Service (SFDPS), Aviation Safety Reporting System (ASRS), National Transportation Safety Board aviation accident database, etc. Computational results on real-world data will be used to showcase the promising performance of machine learning models in facilitating the safety assurance of the air transportation system. 

Speaker

Dr Xiaoge Zhang is currently an Assistant Professor in the Department of Industrial and Systems Engineering (ISE) at The Hong Kong Polytechnic University (PolyU). Before joining ISE at PolyU, he was a Senior Operations Research Analyst in the Operations Research and Spatial Analytics (ORSA) group at the headquarter of FedEx Express in Memphis, Tennessee, United States from March 2020 to August 2021. He received his PhD degree in Systems Engineering and Operations Research at Vanderbilt University, Nashville, Tennessee, United States in 2019. During his PhD studies, he interned at the National Aeronautics and Space Administration (NASA) Ames Research Center (ARC) from August to December in 2016 at Moffett Field, California, working at the Prognostics Center of Excellence (PCoE) led by Dr Kai Goebel. He was a recipient of the Chinese Government Award for Outstanding Self-financed Students Abroad in 2017. Dr Zhang’s research interests include risk & reliability analysis, resilience modeling, machine learning, uncertainty quantification, and data science. He has published more than 40 journal papers in leading academic journals, such as Risk Analysis, IEEE Transactions on Reliability, Decision Support Systems, Information Sciences, Reliability Engineering and System Safety, IEEE Transactions on Cybernetics, and Annals of Operations Research, among others. He is a member of IEEE, INFORMS, and SIAM.