MACHINE LEARNING AND URBAN IDENTITY

Unsupervised machine learning approach to exploring important features of urban identity from the quality of public spaces.

Public spaces play an important role in the processes of formation, generation and change of urban identity. Under present day conditions, the identities of cities are rapidly deteriorating and vanishing. Therefore, the importance of urban design, which is a means of designing urban spaces and their physical and social aspects, is ever growing. This research focuses on developing a novel methodology by using the unsupervised machine learning approach to explore important features of the urban identity from the quantifying quality of public space. The methodologies of quantifying quality of public space are integrated K. Lynch’s work with space syntax and POI. Western and Eastern cities (Zürich and Singapore..etc) will be the case studies to compare and explore the urban identity. This strategy will help to improve planning, design process and generation of new urban patterns with more appropriate features and qualities.

 

Contact: 
Mei-Chih Chang  | chang@arch.ethz.ch