Machine learning for generative architectural design: Advancements, opportunities, and challenges

Generative design has its roots in the 1990s and has become an intense research topic for bringing the power of artificial intelligence to various aspects of architecture practices. The recent advancements in artificial intelligence have made a methodological shift in innovative approaches to generative design, fueled by the proliferation of big data. This paper provides a comprehensive review of emerging machine learning algorithms and their applications in architecture. It investigates the concepts and principles behind machine learning, assesses the strengths and limitations of current algorithms, and examines their applications and exploratory uses with a data-centric approach. This work aims to assess current research, identify emerging opportunities and challenges, and suggest viable solutions for future investigations. This work contributes to a deeper understanding of the rapidly evolving landscape of machine learning in architecture, shedding light on how the field can adapt to and leverage these transformative changes. • Offers a holistic review of the progress in machine learning algorithms for generative architectural design. • Traces generative design evolution, highlighting milestones and design paradigm shifts. • Identifies how architecture is represented and learned through machine learning. • Compares different ML algorithms, outlining strengths and suitability for different architectural applications. • Examines the opportunities and challenges in integrating machine learning into architectural design.