Abstract
Understanding how cities evolve through time and how humans interact with their surroundings is a complex but essential task that is necessary for designing better urban environments. Recent developments in artificial intelligence can give researchers and city developers powerful tools, and through their usage, new insights can be gained on this issue. Discovering a high-level structure in a set of observations within a low-dimensional manifold is a common strategy used when applying machine learning techniques to tackle several problems while finding a projection from and onto the underlying data distribution. This so-called latent manifold can be used in many applications such as clustering, data visualization, sampling, density estimation, and unsupervised learning. Moreover, data of city patterns has some particularities, such as having superimposed or natural patterns that correspond to those of the depicted locations. In this research, multiple manifolds are explored and derived from city pattern images. A set of quantitative and qualitative tests are proposed to examine the quality of these manifolds. In addition, to demonstrate these tests, a novel specialized dataset of city patterns of multiple locations is created, with the dataset capturing a set of recognizable superimposed patterns.
Highlights
Urban patterns within cities are complex and can have heterogeneous structures, and because of this, they are very challenging to simulate
“The Death and Life of Great American Cities”, Jacobs [1] advocates for planning cities that have buildings with mixed primary uses and various age groups, small blocks, and high density
Due to the strong discrepancy of pixel values, such effects will represent a major variation. To avoid this effect and focus our analysis on the semantic differences within city patterns, the data in this research are moved to a canonical form by using data samples that are represented as images with a center that matches that of the captured building cluster
Summary
Urban patterns within cities are complex and can have heterogeneous structures, and because of this, they are very challenging to simulate. Whitehand et al [2] argue that one can comprehend complex phenomena such as urban patterns by creating a picture of them using a minimum number of elements (parameters) These parameters can be viewed as the intrinsic dimensions of an unknown process that generates a city. Jacobs initiated a discussion in the urban planning community by arguing to solve many of the cities’ problems by assisting desirable interactions between agents and highlighting the flaws of a purely top-down approach in planning These dynamics match the ones of complex adaptive systems, and by definition, the prediction of the outcome of such a system with high certainty is not possible. A novel dataset is introduced in the Data Origin and Preparation section This dataset includes multiple city patterns and is designed to contain a known primary semantic variation. The results are discussed along with the limitation in the Discussion, Limitation, and Conclusion sections
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
