Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet
This work addresses the challenge of inconsistent and limited observations in urban planning by providing a scalable, automated method for analyzing urban forms across the planet, which is incremental in applying deep learning to existing data.
The researchers tackled the problem of studying urban forms globally by collecting street network data from over one million cities, towns, and villages and training a deep convolutional auto-encoder to automatically learn hierarchical structures, representing them as comparable vectors. They demonstrated that these vectors enable easy comparison of similar urban forms worldwide and cluster analysis reveals global patterns of urban forms.
Study of urban form is an important area of research in urban planning/design that contributes to our understanding of how cities function and evolve. However, classical approaches are based on very limited observations and inconsistent methods. As an alternative, availability of massive urban data collections such as Open Street Map from the one hand and the recent advancements in machine learning methods such as deep learning techniques on the other have opened up new possibilities to automatically investigate urban forms at the global scale. In this work for the first time, by collecting a large data set of street networks in more than one million cities, towns and villages all over the world, we trained a deep convolutional auto-encoder, that automatically learns the hierarchical structures of urban forms and represents them via dense and comparable vectors. We showed how the learned urban vectors could be used for different investigations. Using the learned urban vectors, one is able to easily find and compare similar urban forms all over the world, considering their overall spatial structure and other factors such as orientation, graphical structure, and density and partial deformations. Further cluster analysis reveals the distribution of the main patterns of urban forms all over the planet.