Authors: Kerry Nice*, University of Melbourne, Jason Thompson, University of Melbourne, Jasper Wijnands, University of Melbourne, Gideon Aschwanden, University of Melbourne, Mark Stevenson, University of Melbourne
Topics: Urban Geography
Keywords: machine learning, urban typology, urban design, transport and health
Session Type: Paper
Start / End Time: 10:00 AM / 11:40 AM
Room: Bayside A, Sheraton, 4th Floor
Presentation File: No File Uploaded
The confluence of recent advances in availability of geospatial information, computing power, and artificial intelligence offers new opportunities to understand how and where our cities differ and also, how they are alike. Departing from a traditional `top-down' analysis of urban design features, this project analyses millions of images of urban form (consisting of street view, satellite imagery, and street maps). A (novel) neural network-based framework is trained with imagery from the largest 1692 cities in the world and the resulting trained models are used to compare within-city locations from Melbourne and Sydney to determine the closest connections between these areas and their international comparators. This work demonstrates a new, consistent, and objective method for understanding the relationship between cities around the world, and the health, transport, and environmental consequences of their design. The results show specific advantages and disadvantages using each type of imagery, and we draw conclusions about the best use of each for specific analytic goals. Finally, and perhaps most importantly, this research also answers the age-old question, ``Is there really a `Paris-end' of your city?''.