主讲人：Hong Kam LO 羅康錦 院长、讲席教授

邀请人： 王书玲 副教授

时间：2025年3月3日15:00 - 17:00

地点：通达馆103会议室

主讲人简介：

Professor Hong K. LO is Dean of Engineering, Chair Professor of Civil and Environmental Engineering and Director of GREAT Smart Cities Institute of the Hong Kong University of Science and Technology. His expertise includes smart city, dynamic transportation system modeling, traffic control, network reliability, and public transportation analysis. He was one of the Most Cited Researchers in Civil Engineering in the Academic Ranking of World Universities (ARWU). Moreover, Professor Lo was elected as Convener of the conference series Advanced Systems for Public Transportation (CASPT), serves as Founding Editor-in-Chief of Transportmetrica B: Transport Dynamics, Managing Editor of Journal of Intelligent Transportation Systems. Professor Lo was awarded the prestigious triennial World Conference on Transportation Research (WCTR) Prize, Eastern Asia Society for Transportation Studies (EASTS) Outstanding Paper Award, and School of Engineering Research Excellence Award. Prof Lo is appointed as a Justice of the Peace (JP) by the Hong Kong government, and is a Fellow of The Hong Kong Institution of Engineers (FHKIE), Fellow of the Chartered Institute of Logistics and Transport (FCILT), Fellow of the Hong Kong Institute of Highway and Transportation (FIHT), Fellow of the Hong Kong Society for Transportation Studies (FHKSTS), and elected as a Fellow of the Hong Kong Academy of Engineering (FHKEng).

主讲内容简介：

Metro systems are often the backbone of metropolitan transit systems due to their high capacity and efficiency. Yet they are subject to disruption. The Mass Transit Railway (MTR) in Hong Kong has an on-time reliability of 99.9%, but still, it has over 200 disruptions per year. The MTR carries about 5 million daily trips. Even if a few percent of the trips are affected by a disruption, tens of thousands of passengers will be affected. Indeed, metro disruption management is an essential element of urban emergency management. This seminar will cover the approach taken to develop a near real-time system developed for use by MTR for metro disruption management, which involves three parts. The first is to analyze the revealed passenger destination choices and train loadings under normal operations and under disruption using smart card (Octopus Card) information. The second is to develop route choice model under disruption by extracting relative route utilities from the metro simulation model and use them to calibrate the utility-based passenger behavior model based on route features. We will also construct a graph neural network (GNN) to capture the complex spatial and temporal information embedded in the metro system for estimating OD diversions. By incorporating the travel choice model and OD diversion model, we will predict the OD and route flows under disruption in a near real-time fashion. Finally, we will illustrate the near real-time system for disruption management developed for MTR.

欢迎各位老师、同学参加同济高等讲堂！

交通学院研究生会
交通学院青年教师沙龙