PhD Oral Exam - Yong Lin Ren, Information and Systems Engineering
Événement
When studying for a doctoral degree (PhD), candidates submit a thesis that provides a critical review of the current state of knowledge of the thesis subject as well as the student’s own contributions to the subject. The distinguishing criterion of doctoral graduate research is a significant and original contribution to knowledge. Once accepted, the candidate presents the thesis orally. This oral exam is open to the public. Abstract This PhD thesis addresses the current need for sustainable freight logistics using HSR, like the corridor Ottawa Quebec, a critical economic artery challenged by congestion, high emissions, and urban-rural disparities. It introduces a novel interdisciplinary framework that integrates high-speed rail (HSR) into intermodal logistics to optimize four core problems: hub location, freight allocation, routing, and mode selection. The methodology combines Graph Neural Networks (GNNs) for spatial representation, Reinforcement Learning (RL) for dynamic decision-making, and fractal geometry to accurately model non-linear accessibility patterns, replacing simplistic Euclidean distances. This approach balances economic efficiency, environmental sustainability (leveraging Quebec’s hydropower), and social equity by incorporating policy constraints such as protected areas and Indigenous lands. Validated through real-world data, comparative analysis with classical models, and global sensitivity analysis (Sobol indices), the framework demonstrates significant improvements—reducing costs, cutting emissions, and enhancing rural service coverage. The research provides a replicable, GNN-driven model for HSR freight integration, supporting decarbonization goals and equitable logistics development in similar mid-latitude corridors worldwide.