Artificial Intelligence in Architecture Studio: Embedding Intelligence in Design


Syllabus


Credits: 4sight, students: Georgios Bekakos, Ray Harli and Lora Fahmy, faculty: Angelos Chronis, 2023

 

Traditionally a sector lagging in the adoption of new technology, architecture is being challenged in the era of artificial intelligence. The imminent convergence of design and technology are not only shaping the way we interact with the physical space, but are also on the verge of redefining the very essence of our built environment. It is clear that AI will become part of the standard toolkit of the AEC professional in the upcoming years and, as architects,  we are perfectly situated in time and expertise to drive the conception and delivery of these AI enabled tools affording performance and efficiency in Architecture. 

This studio seeks to provide a systematic understanding of AI technologies and their potential application  in architecture, exploring the nexus between human creativity and computational intelligence. In an age where data reigns supreme, we delve into the realm of data-driven design processes, embracing open data repositories and open code practices.

The research line develops within three main relevant frameworks:

  • Data Driven Form
  • Embedded performance
  • Integrated Interfaces

The studio work will critically provide AI enabled responses to problems found in the process and output of architecture, essentially  the conception and materialisation of man-made space. We will approach the work from a pragmatic understanding of real and immediate problems, and deliver solutions that integrate with current workflows and platforms. This requires a sequenced approach which we will follow throughout the term:

  • Ideation and problem solution statement
  • Data sourcing and data preprocessing
  • AI  model selection, refinement and training
  • AI model delivery and interface
  • Workflow integration

 


Credits: Latent Studio, student: Alberto Carro Novo, advisor: Oana Taut

 

Learning Objectives

The studio aims to employ the students with fundamental conceptual and practical skills for developing data-driven AI methodologies for urban planning problems. Specifically, the learning objectives of the studio are:

  • Fundamentals of AI applied to the built environment
  • Data collection, engineering and dissemination
  • Development of AI methodologies
  • Deployment and interaction with  of AI models
  • Collective dissemination
  • Visualisation and analysis of data-driven planning
  • Project planning for AI driven projects

Faculty


Projects from this course

NEX.GEN. RETROFIT

NexGen Retrofit Facades leverages AI-driven design to retrofit existing buildings in Barcelona with second skin facades, drastically improving energy efficiency and reducing carbon emissions. buildings & energy systems The building energy systems emit 771,623 tons of co2 PROBLEM Barcelona’s residential buildings, many of which were constructed before modern energy standards, significantly contribute to the city’s … Read more

SAFE MAPS

Safe Maps is a web application that places citizens’ safety at the heart of urban design. By analyzing crime and spatial data, Safe Maps helps build an understanding of the relationship between safety and the urban environment. It then uses machine learning to predict safety scores based on street features, aiding citizens in safely navigating … Read more

Xstream

Xstream is an AI-based plugin in Grasshopper for engineers and architects designing modular research stations in extreme cold environments. The project focuses on developing a Graph Neural Networks system that learns from the geometric data of the modules and the climatic data of the sites to get instant analysis and evaluation of the Environmental and … Read more

Safe Maps

How can AI be used to identify potential safety risks in the city and provide real-time mapping and risk analysis? Safety is a collective priority When using this platform, citizens can both better navigate the existing urban system while also helping drive positive and effective change towards a safer and more secure built environment. Additionally, … Read more

HAVEN AI

A global survey was attempted – by the United Nations – an estimated 100 million people were homeless worldwide. As many as 1.6 billion people lacked adequate housing (Habitat, 2015). In 2021, the World Economic Forum reported that 150 million people were homeless worldwide. SOURCE  Homelessness by Country 2024 (worldpopulationreview.com) “How can we address the … Read more

Wood ID

WoodID is a revolutionary project aiming to transform the utilization and reutilization of wood in the industry. Leveraging artificial intelligence (AI) technology, WoodID targets to enhance the circular model of reutilization by operating within a smaller loop, converting wood into various useful products. The WoodID process commenced with gathering industry insights from Barcelona related to … Read more