Article:

This paper reports on the analytical potential of machine learning methods forurban analysis. It documents a new method for data-driven urban analysis basedon diagrammatic images describing each building in a city in relation to itsimmediate urban context. By statistically analyzing architectural and contextualfeatures in this new dataset, the method can identify clusters of similar urbanconditions and produce a detailed picture of a city's morphological structure.Remapping the clusters from data to 2D space, our method enables a new kind ofurban plan that displays gradients of urban similarity. Taking Pittsburgh as acase study we demonstrate this method, and propose ``morphological types'' as anew category of urban analysis describing a given city's specific set of distinctmorphological conditions. The paper concludes with a discussion of theimplications of this method and its limitations, as well as its potentials forarchitecture, urban studies, and computation.