Rethinking Architectural Design Process using Integrated Parametric Design and Machine Learning Principles - Published conference paper

Aug 4, 2026

Upload by Finn

Artificial Intelligence (AI) can handle large volumes of subjective and conflicting information in architecture, yet it is often used mainly for information management. This work proposes incorporating Machine Learning (ML) into a parametric architectural design workflow so ML mediates between architects’ inputs and end-users’ needs. The objective is to visualize creative designs by transforming information across formats, such as text-to-image or image-to-3D shapes. A process is suggested consisting of model creation, revisualization, and performance evaluation, enabling end-user participation while maintaining output quality through abstraction and processing rather than producing a fully realized final product.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Proposed Approach

Model creation

Revisualization

Performance evaluation

Keywords

Please cite the Published Version Andreou, Alexis, Kontovourkis, Odysseas, Solomou, Solon and Savvides, Andreas (2023) Rethinking architectural design process using integrated parametric design and machine learning principles. In: eCAADe 2023: Digital Design Reconsidered, 20 September 2023-23 September 2023, Graz University of Technology, Austria. DOI: [https://doi.org/10.52842/conf.ecaade.2023.2.461](https://doi.org/10.52842/conf.ecaade.2023.2.461) Publisher: eCAADe Version: Published Version Downloaded from: [https://e-space.mmu.ac.uk/632688/](https://e-space.mmu.ac.uk/632688/) Usage rights: In Copyright Additional Information: This is a conference paper which was presented at eCAADe 2023: Digital Design Reconsidered Enquiries: If you have questions about this document, contact [rsl@mmu.ac.uk. Please](rsl@mmu.ac.uk. Please) include the URL of the record in e-space. If you believe that your, or a third party's rights have been compromised through this document please see our Take Down policy (available from [https://www.mmu.ac.uk/library/using-the-library/policies-and-guidelines](https://www.mmu.ac.uk/library/using-the-library/policies-and-guidelines)) eCAADe 2023 Digital Design Reconsidered Volume 2 Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe 20-22 September 2023 Graz University of Technology Graz, Austria Edited by Wolfgang Dokonal Urs Hirschberg Gabriel Wurzer Editors Wolfgang Dokonal1, Urs Hirschberg1, Gabriel Wurzer2 1Graz University of Technology, Faculty of Architecture 2Vienna University of Technology Wien, Institute of Architectural Sciences, Digital Architecture and Planning 1st Edition, September 2023 Digital Design Reconsidered, Proceedings of the 41st eCAADe conference, 20-22 September 2023, Graz University of Technology Graz, Austria, Volume 2, edited by Wolfgang Dokonal, Urs Hirschberg and Gabriel Wurzer, Brussels: Education and research in Computer Aided Architectural Design in Europe, and Graz: Graz University of Technology, Faculty of Architecture ISBN 9789491207358 (Volume 2) ISSN 2684-1843 Legal Depot D/2023/14982/02 Publisher eCAADe (Education and research in Computer Aided Architectural Design in Europe)– [www.ecaade.org](www.ecaade.org)and Graz University of Technology Faculty of Architecture[https://www.tugraz.at/fakultaeten/architektur/home](https://www.tugraz.at/fakultaeten/architektur/home) Cover Design Alexander Grasser-Parger (rendering by Nikolas Keuschnig) All rights reserved. Nothing from this publication may be reproduced, stored in computerised system or published in any form or in any manner, including electronic, mechanical, reprographic or photographic, without prior written permission from the publisher. Authors are responsible for all pictures, contents and copyright-related issues in their own paper(s) . ii | eCAADe 41 Rethinking Architectural Design Process using Integrated Parametric Design and Machine Learning Principles Alexis Andreou1, Odysseas Kontovourkis 1, Solon Solomou2, Andreas Savvides 1 1 University of Cyprus 2Manchester Metropolitan University 1 {andreou.alexis| [kontovourkis.odysseas|savvides.andreas.1}@ucy.ac.cy](kontovourkis.odysseas|savvides.andreas.1}@ucy.ac.cy)[ ](kontovourkis.odysseas|savvides.andreas.1}@ucy.ac.cy)[2](2 S.Solomou@mmu.ac.uk)[ S.Solomou@mmu.ac.uk](2 S.Solomou@mmu.ac.uk) Artificial Intelligence (AI) has the potential to process vast amounts of subjective and conflicting information in architecture. However, it has mostly been used as a tool for managing information rather than as a means of enhancing the creative design process. This work proposes an innovative way to enhance the architectural design process by incorporating Machine Learning (ML), a type of Artificial Intelligence (AI), into a parametric architectural design process. ML would act as a mediator between the architects' inputs and the end-users' needs.

FAQs

How does the proposed method incorporate machine learning into parametric architectural design?

It integrates Machine Learning (ML) into a parametric workflow so ML acts as a mediator between architects’ inputs and end-users’ needs.

What kinds of transformations does the process aim to support for design visualization?

It targets transforming information from one form to another, such as converting text to image or image to 3D architectural shapes.

What are the main steps of the suggested process?

The method includes model creation, revisualization, and performance evaluation.

Aug 4, 2026

Upload by Finn