Generative design for sustainable architecture: Bibliometric analysis study

As changes in the climate become increasingly noticeable most industries race towards sustainability, the built environment being no exception. Sustainability has become an integral part of architecture. Sustainable solutions such as energy efficiency measures and passive design strategies are implemented in projects of any scale, type, and context. Generative Design (GD) as an exploration process that uses algorithms and computational tools to generate design solutions, considering various design constraints and parameters; it allows for the exploration of a large number of design options and can help identify optimal solutions that are both functional and efficient, offers new opportunities for sustainable architecture in terms of design optimisation. The primary purpose of this thesis is to explore the development of GD for sustainable architecture through a bibliometric analysis of research related to literature on GD for sustainability. In the case study, articles from the Scopus and Web of Science databases are collected and analysed. Graphical representations of the results are obtained using the software VOSviewer and Biblioshiny. According to the results, the most prominent themes are identified, such as machine learning, artificial intelligence, optimization, additive manufacturing, 3d printing, genetic algorithm and BIM. This review may be a reference for future research on GD tools to tackle sustainable design challenges in architectural theory and practice.