Big and Open Data for High-quality Transit Access: Design, Features, and Performance of Multi-modal Transit Catchment Areas revisits the concept of "transit area" and the existing, normative, and future practice of transit area planning against the backdrop of increasing availability and usage of big and open data. Using empirical data and case studies, the book illustrates how transit area can be epitomized and defined in two dimensions: feature (form) and performance (function) and how big and open data and its combination with data from traditional sources can be used to characterize and quantify the two dimensions and to unravel their complex relationships. This book synthesizes the state-of-the-art in how big and open data has been exploited to facilitate transit-area planning and proposes a normative framework for transit-area planning. In this framework, big and open data, alone and in combination with data from traditional sources, can play a role that data from traditional sources alone cannot. The author takes a mixed-method approach to present and convey the contents to the reader. Survey data collected by the author are used to show what kind of big and open data has been and should be used in the current/future transit-area planning practices.
- Introduces how new methods such as gradient boosting decision tree, PageRank, and graph convolutional neural networks can be used to unravel the relationships between transit area features and functions
- Uses a case study method to enhance quantitative analysis of transit areas, including comparative case studies wherever feasible
- Invites the reader to use desktop searches and text mining to explore and visualize the relationships between features and performance of transit areas described in the text, providing a some form of experiential learning
Dr. Jiangping Zhou is Associate Professor and Deputy Director of the Master of Urban Planning program at University of Hong Kong (HKU). He is Chief Examiner of Master of Transport Policy and Planning at HKU. He regularly delivers sessions on big data analytics on public transportation for HKU’s Master of Urban Analytics program. His research focuses on transport/transit systems and land use connections and how to improve their performance. He has published more than 70 articles in English in leading journals such as Proceedings of National Academy of Sciences of the United States of America, Urban Studies, and Journal of American Planning Association. He also has more than 60 refereed articles in the Chinese language. He is currently leading several research projects exploring the nexus of physical infrastructure, land use, and travel behaviors and how better/new data supply/analytics can produce new insights into it and can inform public policies.
