SEMIRAMIS

AI-augmented Architectural Design

Started
October 1, 2021
Status
Completed
Share this project

Abstract

In this research, we developed a methodology for machine learning (ML)-based architectural design. Traditional architectural design involves the combination and optimization of numerous criteria and constraints. For performance-driven design, architects and engineers often use parametric models to generate, simulate, and evaluate multiple design instances, gathering performance feedback on design modifications. However, this process is typically hierarchical, limited in its ability to handle multiple concurrent objectives, and explores only a narrow portion of the design space. In contrast, we applied generative machine learning models to effectively find and explore design instances that are close to specified performance goals, bypassing the need for extensive manual tuning of input parameters. We implemented this approach in the open-source AIXD (AI eXtended Design) toolkit, which has been successfully applied to various domains beyond architecture, including the design of mechanical components, load-bearing structures, and notably, Semiramis, a vertical garden structure in Zug, Switzerland.

People

Collaborators

SDSC Team:
Luis Salamanca
Alessandro Maissen
Fernando Perez-Cruz

PI | Partners:

ETH Zurich, 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

EMPA:

  • Dr. Kurt Heutschi

More info

Rocket Science:

  • Christian Frick

More info

description

Motivation

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 human best-guess or they are limited to blanket solutions. Parametric design tools such as Grasshopper allow the automated generation of large numbers of potential solutions, and the integration of performance measures. Still, parametric modelling (Figure 1) only allows to carry out forward design, which still restrict the exploration capabilities of the designer, and a broader exploration of the solution space.

Figure 1: Schematic representation of the traditional parametric modelling paradigm

Proposed Approach / Solution

We have implemented a methodology for inverse design that leverages the traditional parametric model. By using design instances generated using the parametric model, we can train a ML model (see Figure 2) to carry out two tasks. First, accelerate forward modelling by learning a surrogate model of the mapping from design parameters to performance measures. Second, perform inverse design, i.e., given a set of desired performance measures, the trained model will suggest designs satisfying those. Specifically, we have leveraged autoencoders, as in this architecture we can use the trained encoder as surrogate model, and the decoder as generator. We have implemented this methodology in an open-source toolbox called AIXD (AI eXtended Design).

Figure 2: AI-augmented modelling paradigm for forward and inverse design

Impact

This methodology unleashes novel design possibilities by offering designers insights into solutions they might not have otherwise imagined. It helps mitigate unconscious bias and enables the combination of human synthetic thinking with the analytical power of computation. Furthermore, through the AIXD toolbox intend to bridge the gap that exists between designers and ML methodologies. We address this by abstracting away the complexity of deploying use-case specific ML models, and by providing tools for design exploration, performance-driven generation, etc. We have applied this approach in several use cases, such as Semiramis (see Figure 3), a vertical garden structure built in Zug, Switzerland. We believe this design paradigm, supported by ML tools, can enhance human intuition about design problems and enable a more exhaustive and efficient exploration of the solution space.

Figure 3: The vertical garden “Semiramis“ 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 occlusion and rain occlusion, c) the final design visualized in context and scale.

Gallery

Annexe

Bibliography

  1. Nauata, N., Chang, K. H., Cheng, C. Y., Mori, G., & Furukawa, Y. (2020). House-gan: Relational generative adversarial networks for graph-constrained house layout generation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16 (pp. 162-177). Springer International Publishing. https://doi.org/10.1007/978-3-030-58452-8_10
  2. Oh, S., Jung, Y., Kim, S., Lee, I., & Kang, N. (2019). Deep generative design: Integration of topology optimization and generative models. Journal of Mechanical Design, 141(11), 111405. https://doi.org/10.1115/1.4044229
  3. Brown, N. C., & Mueller, C. T. (2019). Design variable analysis and generation for performance-based parametric modeling in architecture. International Journal of Architectural Computing, 17(1), 36-52. https://doi.org/10.1177/147807711879949
  4. Sohn, K., Lee, H., & Yan, X. (2015). Learning structured output representation using deep conditional generative models. Advances in neural information processing systems, 28. Learning Structured Output Representation using Deep Conditional Generative Models

Publications

Apolinarska, A. A.; Casas, G.; Salamanca, L.; Kohler, M. "ARA - Grasshopper Plugin for AI-Augmented Inverse Design" Scalable Disruptors 231-240 2024 View publication
Apolinarska, A.; Salamanca, L.; Casas, G.; Kraus, M.; Kuhn, S.; Maissen, A.; Rust, R.; Tatsis, K. "AIXD" Available at: https://app.data-archive.ethz.ch/delivery/DeliveryManagerServlet?dps_pid=IE34426837 2024 View publication
Salamanca, L.; Apolinarska, A. A.; Pérez-Cruz, F.; Kohler, M. "Augmented Intelligence for Architectural Design with Conditional Autoencoders: Semiramis Case Study" Towards Radical Regeneration 108-121 2023 View publication
Patel, N.; Salamanca, L.; Barba, L. "Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance" Preprint 2023 View publication

More projects

LUCID National Data Stream

In Progress
Low Value of Care in Medical Hospitalized Patients - a National Data Stream on Quality of Care in Swiss University Hospitals
Health & Biomedical

Syngenta: Steam consumption optimization

Completed
Reliable strategies to save energy in Syngenta’s Kaisten plant
Energy & Sustainability
Private sector

Pilot project ENERBAT

Completed
Data-Driven Pathways to Net Zero for the Canton of Vaud’s Building Portfolio
Energy & Sustainability
Climate & Environment
Public sector

EKZ: Synthetic Load Profile Generation

Completed
Reliable electricity load monitoring for non-metered nodes
Energy & Sustainability
Public sector

News

Latest news

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland
May 7, 2026

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Coding the Future: Energy Data Hackdays Expand to French-speaking Switzerland

Held at the SDSC headquarters at Biopôle, the Energy Data Hackdays gather 100 experts to tackle 5 energy and grid challenges.
Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués
April 30, 2026

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Science des données : le SDSC et le Canton de Vaud soutiennent quatre projets appliqués

Le SDSC et le Canton de Vaud ont retenu quatre projets parmi les 57 soumissions reçues lors de leur deuxième appel à projets.
Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne
March 12, 2026

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le Swiss Data Science Center inaugure son siège au Biopôle de Lausanne

Le SDSC inaugure aujourd'hui son siège au campus Biopôle de Lausanne, dans le cadre d'un partenariat stratégique avec l'État de Vaud.

Contact us

Let’s talk Data Science

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