AI-augmented architectural design

June 1, 2019
Share this project


This research project aims to develop a toolkit for ML-based architectural design.

Traditionally, architectural design involves combining and optimizing many criteria and constraints. For performance-driven design, architects and engineers create parametric design models to generate, simulate and evaluate many design instances, to gather performance feedback on design alterations. However, this is typically a hierarchical process, unable to deal with multiple concurrent objectives and only investigating a narrow spectrum of the design space.

Here, instead of tuning input parameters until the result meets certain performance criteria, we envision that machine-learned models of the design problem will allow us to find and explore design instances in the proximity of the specified performance goals.

We will develop and validate our AI-Augmented Architectural Design (AAAD) toolkit with a generic approach through case studies that are based on two different design categories. The first category concerns 2.5D surfaces, which are evaluated based on their fabricability (for 3D contour printing) and on environmental performance such as acoustics or sunlight protection, targeting architectural applications such as acoustic panels and façade panels. The second category is discrete element assemblies, which comprise load-bearing structures made of columns and beams. This category is evaluated based on structural or environmental performance goals.

The ultimate goal of this project is to augment the designer’s creative and analytical capabilities in the decision-making process by creating interactive design environments and thus revolutionizing computational design methods in architecture.



SDSC Team:
Fernando Perez-Cruz
Luis Salamanca

PI | Partners:

Gramazio Kohler Research:

  • Prof. Matthias Kohler
  • Prof. Dr. Arno Schlüter
  • Dr. Aleksandra Anna Apolinarska
  • Dr. Romana Rust

More info

University of Bremen:

  • Prof Dr. Dr. Norman Sieroka

More info

Strauss Electroacoustic:

  • Jürgen Strauss

More info


  • Dr. Kurt Heutschi

More info

Rocket Science:

  • Christian Frick

More info



Design in Architecture, Engineering and Construction (AEC) can be described as an ill-defined (“wicked”) problem with many parameters, multiple constraints, and contradicting objectives. Traditionally, only a very small number of possible solutions is considered, created based on a human best guess or they are limited to blanket solutions. Parametric design tools such as Grasshopper allowed the automated generation of large numbers of potential solutions and the integration of performance measures. We aim to learn a generative model from the samples obtained from the parametric design that enables, given some desired performance attributes, generating a range of solutions that satisfy such constraints.

Proposed approach:

This will unleash novel design possibilities by augmenting the designers with insights into solutions they could not have imagined, excluding their unconscious bias, and allow them to combine human synthetic thinking with the analytic power of computation.


The SDSC leads the WPs related to the development of the ML/DL methodologies, which revolves around two different case studies that will boil down into a general methodology for generative design in AEC. The development of an interactive toolkit will is lead by the partners, with our contribution.


Figure 1: The proposed approach will allow the designer to discover new designs for given performance attributes, and interrogate the design space upstream.
Figure 2: The vertical garden project:
a) the outline shapes of the planting platforms are generated from the design parameters (radii and constellations).
b) the design is subsequently assessed w.r.t. total area of the platforms, sun and rain occlusions.
c) the final design visualized in context and scale.


Additionnal resources


  1. N. Nauata, K.-H. Chang, C.-Y. Cheng, G. Mori, and Y. Furukawa, ‘House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation’, arXiv:2003.06988 [cs]​, Mar. 2020, Accessed: Oct. 26, 2020. [Online]. arXiv
  2. S. Oh, Y. Jung, S. Kim, I. Lee, and N. Kang, ‘Deep Generative Design: Integration of Topology Optimization and Generative Models’, ​J. Mech. Des,​ vol. 141, no. 11, Nov. 2019, doi: 10/gg2m8v.
  3. N.C. Brown and C.T. Mueller, ‘Design variable analysis and generation for performance-based parametric modeling in architecture’, ​International Journal of Architectural Computing​, vol. 17, no. 1, pp. 36–52, Mar. 2019, doi: 10.1177/1478077118799491.
  4. K. Sohn, H. Lee and X. Yan. ‘Learning struc- tured output representation using deep conditional generative models’. In Cortes, C., Lawrence, N., Lee, D., Sugiyama, M. & Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, 3483–3491 (Curran Associates, Inc., 2015). PDF


More projects


In Progress
Machine Learning for the Future Circular Collider Design
Big Science Data


In Progress
Real-time cleansing of snow and weather data for operational avalanche forecasting
Energy, Climate & Environment


In Progress
Extracting activity from large 4D whole-brain image datasets
Biomedical Data Science


In Progress
Deep statistical learning-based image analysis for measurement of socioeconomic development in sub-Saharan Africa using high-resolution satellite images, and geo-referenced household survey data
Energy, Climate & Environment


Latest news

PassGPT | Using language models to enhance password security
February 6, 2024

PassGPT | Using language models to enhance password security

PassGPT | Using language models to enhance password security

PassGPT is a Large Language Model for password generation trained on leaked passwords, which can outperform existing methods based on generative adversarial networks by guessing twice as many unseen passwords.
ADORE | A benchmark dataset in ecotoxicology to foster the adoption of machine learning
January 24, 2024

ADORE | A benchmark dataset in ecotoxicology to foster the adoption of machine learning

ADORE | A benchmark dataset in ecotoxicology to foster the adoption of machine learning

Applying machine learning to ecotoxicology could help reduce the number of animal tests, costs, and animals sacrificed while preserving the accuracy of the in vivo tests.
License Flowers | Art and AI at SDSC
February 21, 2024

License Flowers | Art and AI at SDSC

License Flowers | Art and AI at SDSC

An adventure to create art using AI to raise awareness on code licenses

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!