Machine Learning for the accessibility to urban scale analysis

Abstract

This paper proposes the use of Machine Learning to simplify and make accessible the obtaining of complex analyses’ results, particularly in the assessment of thermal comfort on the urban scale. The complex relationship between planning, city shape, and climate requires the use of strategies for analyzing and producing urban space that often exceeds the planner's expertise. Building tools that, besides powerful, make it easier and faster for planners to act quickly and continuously, requires thinking about the trade-off between accuracy and speed of the methods applied. From a technological, political, and environmental point of view, the proposed method aims to improve the understanding of the implications of buildings on the urban environment and to contribute to the production of the contemporary city through the construction of information.