Future of Urban Design Through Generative Design Tools

Abstract

The increasing accessibility to dynamic data collected from low-cost sensing and crowd-sourced technologies, and geo-localized mobile and social media networks, are generating new types of data analysis practices. Such practices are opening new possibilities to rethink urban planning processes to address pressing urban contemporary challenges such as urban health and comfort. The study of dynamic data can enable the development of adaptable urban environmental and mobility planning strategies; however, the implementation of the data analysis protocols in urban design and planning strategies still remains to be further discussed. This chapter presents several research case studies focused on the utilization of dynamic data sources and machine learning technologies, for the study and prediction of urban environmental gradients and mobility patterns. The chapter argues that the presented research workflows can enable a high spatiotemporal resolution urban field exploration which was not possible with the traditional sensing and traffic monitoring platforms. Furthermore, the chapter argues that dynamic data-driven methodological approaches can inform real-time urban planning strategies such as the adjustment of transportation, bike and micro mobility routes, or public space configuration strategies to minimize the exposure to air pollution or heat stress.