Urban-GAN: An artificial intelligence-aided computation system for plural urban design

Abstract

The current urban design computation is mostly centered on the professional designer while ignoring the plural dimension of urban design. In addition, available public participation computational tools focus mainly on information and idea sharing, leaving the public excluded in design generation because of their lack of design expertise. To address such an issue, this study develops Urban-GAN, a plural urban design computation system, to provide new technical support for design empowerment, allowing the public to generate their own designs. The sub-symbolic representation and artificial intelligence techniques of deep convolutional neural networks, case-based reasoning, and generative adversarial networks are used to acquire and embody design knowledge as the density function, and generate design schemes with this knowledge. The system consists of an urban form database and five process models through which the user with little design expertise can select urban form cases, generate designs similar to those cases, and make design decisions. The Urban-GAN is applied to hypothetical design experiments, which show that the user is able to apply the system to successfully generate distinctive designs following the urban form “styles” in Manhattan, Portland, and Shanghai. This study further extends the discussion about the plural urban design computation to general reflections on the goals and values in AI technique application in planning and design.

Analysis and Reconstruction Method of Spatial Characteristics of Traditional Chinese Villages Based on Parameterization

“…It is necessary to consider a range of objectives, encompassing both objective constraints, such as land rights heritage conservation, and subjective factors, such as culture, social systems, economy, and aesthetics. In future studies, deep learning methods can be applied to the process of extracting spatial features and organizational rules, to accurately perceive and recognize complex spatial forms [39][40][41], minimizing manual intervention during the generation process. In addition, it is necessary to multidimensional optimization parameterized content system, incorporate "invisible" indicators such as social and economic development, human demands, sociocultural and institutional structures into the parameterized indicator system.…”

Analysis and Reconstruction Method of Spatial Characteristics of Traditional Chinese Villages Based on Parameterization

“…In recent years, breakthroughs have been made in the research of artificial intelligence assisted planning and design. Through machine learning of a large number of real cases, case features are extracted, enabling the recognition and extraction of villages' spatial forms with strong locality and adaptability [60][61][62]. This approach minimizes manual intervention in the generation process and addresses the issue of manually selecting generation rules and adjusting parameters in parametric design methods.…”