Â鶹ÒùÔº

Skip to main content

Seminar: Machine Learning-enhanced Predictive Modeling in Air Traffic Management - Mar. 6

Yutian Pang

Yutian Pang
Machine Learning Research Engineer, Thales
Wednesday, Mar. 6 | 9:30 a.m. | AERO 111

Abstract: National Airspace Systems (NAS) are cyber-physical systems that require swift air traffic management (ATM) to ensure flight safety and efficiency. With the surging demand for air travel and the increasing complexity of aviation systems, the imperative for automation to support air traffic management and air traffic control (ATC) service has reached unprecedented levels. Machine learning models draw insights from historical experiences and observations, shows immense potential to address the aforementioned challenges by providing recommendations and decision supports within machine time. This seminar first presents research study on mitigating the impact of convective weather on flight trajectories, to address weather-related aviation safety concerns. In this work, a weather-related flight trajectory plan calibration method is proposed. Then, the seminar discusses a method for probabilistic multi-aircraft trajectory prediction in the near-terminal airspace, leaveraging the cutting-edge AI model and aviation domain knowledge. The third part of this seminar introduces a machine learning-enhanced aircraft landing sequencing method to improve the landing efficiency. In this work, the minimum landing separation time predicted from probabilistic machine learning serves as the optimization constraints for better landing sequencing. In conclusion, several promising and impactful research directions using AI in aerospace engineering are discussed, along with preliminary investigations.

Bio: Yutian Pang is currently a machine learning research engineer at Thales, where he works on AI/ML R&D for digital and cyber security topics in critical engineering domains. Yutian obtained his bachelor’s degree in mechanical engineering from Huazhong University of Science and Technology in 2017, and received his master's and Ph.D. degrees from Arizona State University in 2018 and 2023, respectively. His research interests are applied machine learning research to various aviation/aerospace topics with focuses on machine learning uncertainty, robustness, and safety.