top of page
fig1_rev.jpg

Intelligently combining design features of different designs can yield radically new functional designs.

AI in Architecture and Urban Design 

 

Collaborators: Imdat As + Prithwish Basu

Project Start: Jan 2018

Funding: DARPA (Defense Advanced Research Projects Agency) Grant (Completed)

Researchers: 5

Status: Completed

 

DESCRIPTION: 

Artificial intelligence, and in particular machine learning, is a fast-emerging field. Research on artificial intelligence focuses mainly on image-, text- and voice-based applications, leading to breakthrough developments in self-driving cars, voice recognition algorithms and recommendation systems. In this project we worked on an alternative graph-based machine learning system that deals with three-dimensional space, which is more structured and combinatorial than images, text or voice. Specifically, we explored a function-driven deep learning approach to generate conceptual design. We trained and used deep neural networks to evaluate existing designs encoded as graphs, extract significant building blocks as subgraphs and merge them into new compositions. Finally, we explored the application of generative adversarial networks to generate entirely new and unique designs.

​

PUBLICATIONS: 

  • Mehmet O. Senem, H. Tunçay, M. Koç, I. As, “Generating Landscape Layouts with GANs and Diffusion Models,” Journal of Digital Landscape Architecture, 9-2024, pp. 137-144

  • Mehmet O. Senem, M. Koc, I. As, “Using Deep Learning to Generate Front and Backyards in Landscape Architecture,” Hybrid Space of the Metaverse: Architecture in the Age of the Metaverse, Opportunities and Potentials, 10th ASCAAD Conference, Lebanon, 12-13 Oct 2022, pp. 2-16.

  • Imdat As, P. Basu, Artificial Intelligence in Urban Planning and Design: Technologies, Implementation, and Impacts, New York: Elsevier, May 6, 2022.

  • Elcin Sarı, C. Erbas, I. As, "The Image of the City through the Eyes of Machine Reasoning," Artificial Intelligence in Urban Planning and Design, Technologies, Implementation, and Impacts. Editors: Imdat As, Prithwish Basu and Pratap Talwar. Elsevier, May 2022. 

  • Elcin Sarı, P. Basu, I. As, "A Machine Learning Approach for Locating Businesses along Main Arteries in Inner Cities," IEREK Conference, Future Smart Cities, Dec 2021

  • Elcin Sarı, H. Sacın, S. Yigitarslan, C. Erbas, I. As, "A Machine Reasoning Approach to Identify Design Patterns from City Layouts," IEREK Conference, Future Smart Cities, Dec 2021

  • Imdat As, P. Basu, S. Burukin, "AI in crowdsourced design,” The Routledge Companion to Artificial Intelligence in Architecture. Chapter 19. Editors: Imdat As, Prithwish Basu. New York: Routledge, 2021.

  • Prithwish Basu, I. As, E. Munch, "Generating new architectural designs using topological AI,” The Routledge Companion to Artificial Intelligence in Architecture. Chapter 9. Editors: Imdat As, Prithwish Basu. New York: Routledge, 2021.

  • Kaan Karabagli, M. Koc, P. Basu, I. As, "Using AI to turn graph representations into conceptual massing models," SIGraDI2021 Designing Possibilities Conference, Aug 2021, pp. 191-202.

  • Imdat As and Prithwish Basu, The Routledge Companion to Artificial Intelligence in Architecture, New York: Taylor & Francis, May 2021.

  • Composing Frankensteins: Data-driven design assemblies through graph-based deep neural networks,” (with Prithwish Basu and Siddarth Pal) Computer Composition: Design after Machine Learning, 107th ACSA Conference, Carnegie Mellon University, Pittsburgh, PA, March 28-30, 2019.

  • Artificial intelligence in architecture: Generating conceptual design via deep learning,” (with Prithwish Basu and Siddarth Pal), International Journal of Architectural Computing (IJAC), Vol. 16, Issue 4, 2018: 306-327.

​

INTERVIEWS GIVEN:

​

PRESENTATIONS, PANELS AND LECTURES:

  • Iyi Tasarim/Good Design Izmir_5, “Artificial Intelligence, the Designer’s Perspective,” Panel Discussion, ZOOM Webcast, Dec 18, 2020.

  • 107th ACSA Conference, “Composing Frankensteins: Data-driven design assemblies through graph-based deep neural networks,” Computer Composition: Design after Machine Learning, Carnegie Mellon University, Pittsburgh, PA, March 28-30, 2019.

  • Hochschule Wismar, University of Applied Sciences, Technology, Business and Design, “24 hours Berlin City West,” International Workshop on the Future City in Berlin, Germany, March 16-24, 2019.

  • Bilkent University, “The Future is History: Architecture in the Age of Artificial Intelligence,” Ankara, Turkey, 2018.

Topological summary of latent design rules of architectural data generating automated designs.

Topological summary of latent design rules of architectural data generating automated designs.

fig-erc1.jpg

Discovering latent building blocks in design data using deep learning and topological data analysis.

bottom of page