The rapid evolution of the aviation industry, combined with increasing competitive pressures and the demand for optimized operational efficiency, has driven airlines to explore advanced methodologies for performance prediction and decision-making. At the same time, the industry's significant contribution to resource depletion and global climate change, primarily due to fossil fuel combustion and the resulting CO2 emissions. As a result, there is an urgent need for system-level research in the aviation sector to inform and guide environmental policies, ensuring that the industry fulfills its economic and ecological responsibilities.
In this context, accurately modeling specific operational parameters is crucial for effectively simulating airline operations. These key parameters often exhibit complex interrelationships that traditional linear models struggle to capture. Therefore, it is essential to develop and apply a neural network-based model to predict additional critical parameters using publicly available operational data. This model aims to establish robust predictive relationships, offering valuable insights for simulating and optimizing airline operations.
As part of this Master's thesis, the potential relationships between various operational parameters within airlines will be investigated through neural modeling. The objective is to develop a neural network model that identifies the corresponding influences between key operational parameters and the magnitude of these influences.
If this fits your interest, please contact: Hongfeng Gao
Important note on the supervision of Master's theses: A successfully completed Master's specialization (10 ECTS) in Production and Logistics is required. This thesis is to be completed exclusively in English.