Skip to main content

2024 | Book

Creativity in the Age of Digital Reproduction

xArch Symposium

Editors: Giancarlo Di Marco, Davide Lombardi, Mia Tedjosaputro

Publisher: Springer Nature Singapore

Book Series : Lecture Notes in Civil Engineering


About this book

Inspired by this symposium we would like to rethink and provide an insight about the use of new technologies in architecture and design. The consideration spans over (but not limited to) computational design, virtual experience, digital fabrication, artificial intelligence and sustainability/environment. Readers of the proceedings will benefit from discussions on how adoption of new technologies can benefit the Construction Industry rather than just for the sake of leveraging new technologies. The book targets scholars and high-education level students, as well as Ph.D.s which research falls into the broad realm of digital design.

Table of Contents

Creativity in the Age of Digital Reproduction
Giancarlo Di Marco, Mia Tedjosaputro, Davide Lombardi

Computational Design Session

Architectural Design Under Pandemic of Today's AI: From Human-Computer Interaction (HCI) to Human-Machine Conversation (HMC)

Human-computer interaction (HCI) has been explored in the architecture discipline since the 1960s. It stated that humans and architecture (as machines) are both designers. However, with the rapid growth of AI in recent years, misusing AI has resulted in social problems, as named the “pandemics of today's AI” by Paul Pangaro. This paper aims to find insights into the causes and potential ways of taming the situation, followed by proposing a paradigm for developing HCI-based architecture in the future. Key HCI-based projects and recent developments will be analysed through major academia and research bodies. This research identifies three findings, including blurred definitions of interactivity, loss of physicality and lack of real-world application. Hence, we propose focusing on Human-Machine Conversation (HMC) as a more directed approach to developing HCI in architecture. This focus emphasises the “machine” as a focus on the physical built environment and “conversation” as the most critical interaction for future architecture.

Lok Hang Cheung, Juan Carlos Dall’Asta, Giancarlo Di Marco, Asterios Agkathidis
Creativity at the Edge of Digital Reproduction — from Coop Himmelb(l)au to Deep Himmelb(l)au

New architectural technologies have been developed, and established throughout history, and this continues to be the case today. Looking at the Austrian-based architecture studio Coop Himmelb(l)au’s complex set of avant-garde design processes, this paper reflects upon the implications of recent and continuing advances in technologies within the fields of digital design, robotic fabrication, and artificial intelligence (AI) in the Age of Digital Reproduction, and within that purview, asks how such creativity can remain at the Edge of Digital Reproduction. Accordingly, I look back at such pivotal projects as Rooftop Remodelling Falkestrasse, Groninger Museum – the East Pavilion, BMW Welt, and Pavilion 21 Mini Opera Space; and forward at robotic fabrication processes applied in the Shenzhen Museum of Contemporary Art & Urban Planning Exhibition and the Musée des Confluences, as well as virtual and augmented reality applications and machine learning (ML) tools that are a part of the ongoing Deep Himmelb(l)au research, which we expect to transform certain techniques of the architecture industry, affect aesthetic invention itself and perhaps even bring about an extraordinary change in our very definition of architecture.

Lei Feng
Computing Analogue Interactive Installations

This paper documents the development and application of a set of computational tools and fabrication methods to support and facilitate the design, simulation and realization of 3D Moiré Animation installations. Setting-out from the technique of traditional 2D Moiré Animations, the authors developed tools to examine a novel approach which combines the depth of field and motion of the spectator to achieve large-scale, analogue animations in three dimensions. Furthermore, the authors suggest that large scale outcomes can enhance the way people interact with outdoor spaces. For that hypothesis the particular paper illustrates the application of the tools for the realization of two large-scale interactive analogue motion graphic installations; a memorial and a temporary centrepiece for a dance festival in Cyprus. The tools operate as a free plugin for Grasshopper 3D and can be downloaded.

Michail Georgiou, Odysseas Georgiou, Eva Korae
UAV-Based Geometry Data Acquisition for Building Energy Modelling

Building Energy Modelling (BEM) is a critical tool for various building energy-related applications, such as energy efficiency diagnosis, certification, and retrofit design. Accurate building geometric, non-geometric, and weather data are crucial for effective BEM. Conventional onsite measurement methods can be laborious and time-consuming. Furthermore, after the onsite work, creating the energy simulation model has disproportionately outweighed the attention given to high-value engineering and energy analysis within the retrofit workflow. Unmanned Aerial Vehicles (UAVs) enable swift data collection, bypassing lengthy manual processes and offering potential solutions. This study used aerial imagery captured by a UAV to create a geometry model of a residential building in Suzhou, China, aiding energy assessment. Specialised software can convert photos into a detailed 3D model while lacking semantic information limits its utility beyond visualisation. Therefore, post-processing was conducted to generate a complete geometric model. The outcomes were compared to conventional measurement methods against accuracy and processing time. The study demonstrates that the application of UAV-based photogrammetry can semi-automatically reconstruct the building envelope with high precision, providing valuable geometry input for building energy assessment.

Mengfan Jin, Marco Cimillo
Cellular Automata as Design Tools for Artificial Ecologies

The built environment functions as a facilitator of a healthy relationship between humans and the natural environment. The ability of cellular automata (CA) to model naturally occurring phenomena that express in spatio-temporal patterns offers opportunities to both simulate and generate complex spatial arrangements based on local morphological rules. This local relationship-driven property resonates with the local generative dynamics found in natural systems. To address the intricacies associated with cellular automata rule definitions within the context of ecological urban form, we construct a “multi-layered” CA as a theoretical model for exploring ecological performance-oriented architectural form design. The resulting model accommodates both conventional top-down design strategies and the locally driven relational networks of ecological considerations. An analysis of two case studies not only examines the possibilities of both simulating and generating ecologically oriented, integrated architectural and urban form using CA-based strategies at different stages of the design process, and offers designers a new way to model and evaluate ecologically sensitive constructed environments.

Yiming Liu, Christiane M. Herr
Deployable Origami Wall with Patterned Knit Panels

This paper explores the process of creating a unique triangulated origami folding wall, highlighting its relevance to design as research and research through design. By integrating hand-making techniques with digital methodologies, the project challenges traditional design methods in architecture.The design process involved a process of hand to digital and digital-to-hand for the different elements of the project. Using Rhino3D and Grasshopper to simulate various pattern designs, which were then ultimately fabricated by hand. Meanwhile, paper origami hand models inspired the overall frame structure, which was later modeled, in Rhino3D and Grasshopper to simulate the folding process.While designs were simulated both digitally, the use of digital tools is used during different phases of the design, emphasizing the potential of parametric thinking alongside manual creation.Hand-making techniques, including domestic knitting machines and hand-manipulated stitches, were used to craft detailed and customized panels. Varying pattern densities created a dynamic interplay of light and shadow. The design for the pattern is based on a binary pattern of stitches and floats, harkening back to early coding and jacquard looms and punch cards.These knitted panels are attached to the folding frame design to create a wall system that is spatially dividing but also plays with porosity. The design allows some light and shadow play as well as varying density and depth between the layers.The project demonstrates the potential of blending computational design with manual development in architectural design. While working through this research on the relationships between physical and digital production as a means for design artifacts.

Virginia Ellyn Melnyk
Critical Social Computing for Digital Design

Advancements in computational technology have ushered in a new era of architectural design, characterized by the integration of digital tools. However, this rapid pace of technological innovation has also widened the digital divide, making advanced design solutions less accessible, particularly in underprivileged regions and marginalized communities. Meanwhile, data and algorithmic processes profoundly impact the post-digital built environment. With increasingly complex problems of the built environment, such communities are at risk unless this gap is addressed. This paper underscores the significance of regional computing systems, referred to as social computers, and their emergence in addressing these disparities. To allow architects and experts to act as facilitators of resilience and transformation, critical social computing for design is proposed as a strategy to develop meaningful collaborative practices through digital tools. Through illuminating case studies, instances are identified where architects and experts collaborate as co-coders of social computing, fostering bottom-up approaches to address increasingly intricate challenges in a post-digital world.

Muhammad Talha Muftee
Data-Responsive Architecture in Urban Open Space: Sensing Social and Environmental Data and Regulating Spatial Configuration in Real-Time

The design experiment aimed to examine the application of data-processing techniques to regulate a responsive architectural space. The experiment involved simulating an active system of adaptive space that comprised kinetic structures capable of responding to real-time changes in social events and environmental conditions situated in an open space in New York City. The study tested the application of rule-based algorithms that utilise predefined rules to determine the behaviours of kinetic structures by manipulating data. The rule-based algorithm processed the input of urban open data that captured the phenomenon in the open space, resulting in controlling the spatial configurations of kinetic structures. This involved the act of categorisation, classifying the location, schedule, and type of social event data, as well as calculating numeric values of weather parameters such as temperature, cloud cover, humidity, and wind speed to optimise spatial qualities with respect to light/shading, weather conditions, and access. The challenge of the experiment was to create an algorithm that was not only reactive to the input data in real time but also intelligently responsive, providing optimised conditions of an architectural space that adapts to the contexts of both social and environmental changes. The results of the experiment demonstrate the potential for the development of computational techniques to create intelligently responsive spaces in the built environment.

Hyunjae Nam
Design of the Intelligent Bridge Drainage Monitoring and Control System

When a bridge spans over water, traffic accidents or hazardous chemical spills may result in pollutants entering the waterway through the runoff on the bridge surface, causing water pollution. This study aims to address the shortcomings of existing bridge drainage systems, such as environmental unfriendliness, low efficiency, and difficult maintenance, and to achieve intelligent and informational control of bridge drainage valves. To achieve this, we developed a bridge drainage intelligent control system based on the existing drainage system of the bridge, using Internet of Things (IoT) technology, machine learning technology and information visualization technology. The system consists hardware modules for detecting bridge surface conditions, long-distance wireless communication modules, intelligent drainage valves, and a server monitoring terminal. When a special situation occurs on the bridge surface, the server monitoring terminal will present real-time information on the bridge and send timely instructions to control the intelligent drainage valves to prevent pollutants from being discharged into the water. This study explores a safe, efficient, and environmentally friendly bridge drainage mode, contributing to the construction of a digital-era urban bridge information management system.

Danni Zheng, Yiheng Feng, Li Li
SAUCE – SpAcevehicle-bUilding Connectivity Evaluation
An Adjacent Matrix Based Digital Tool for Internal Connectivity Evaluation and Improvement in Spacevehicle-Buildings

Spacevehicle-building represents a peculiar design problem with many stringent requirements, including unusual surrounding conditions and severe cargo limitations. The latter is caused by the launch system capabilities and impacts on the internal room’s dimensional and mass characteristics. Therefore, one of the Spaceship’s design challenges consists of its internal room organisation considering the needs under holistic perspectives. In particular, it is crucial “how” internal rooms are related since their optimal use depends on well-defined connections.SAUCE proposes an automatised tool that evaluates internal connections’ performance in Spacevehicle-Buildings by digitalising the Adjacency Matrix. This method is used in architectural design to represent the relationship between rooms while its digitalisation will bring the readability and execution by a machine. The proposed tool provides a computable and objective assessment of “how” the internal functions are related to each other, describing a Spacevehicle-Building internal organisation from spatial layout perspective. Implementation of this workflow include feeding the scoring system to a metaheuristic algorithm-based generative process to investigate optimal combinations between the functions, providing support to the design process.

Zhelun Zhu

Digital Experience Session

Challenges and Opportunities in Using Digital Pedagogy for Game-Based Architecture Education: A Case in China

Digital pedagogy (DP) has received increasing attention from different disciplines to study the dedicated use of contemporary digital technologies (e.g., virtual learning environments and digital media platforms) for inclusive and personalized learning and teaching. Applying DP appropriately can help teachers to shift from traditional instruction methods towards more interactive and engaging approaches for high-quality education. Under the umbrella of DP, digital game-based learning (DGBL) represents a pedagogical approach that utilizes interactive and immersive digital games to nourish the development of critical thinking and problem-solving skills for student-centred active learning. However, how teachers can apply DGBL effectively in architecture education is still being determined. We conducted a qualitative case study to explore student engagement after implementing the DGBL pedagogy supported by H5P escape room learning activities in an architecture course with 121 university students. Our study found that the game elements and the characteristics of Architecture education influenced students’ learning engagement in four aspects (behavioural, emotional, cognitive and social). The main research findings contribute to digital pedagogy by extending people’s understanding of the DGBL’s impact on learner engagement with rich empirical data. Limitations and practical implications were discussed for future development.

Silvia Albano, Wan Meng, Wenruo Xu, Na Li
Digital Creativity in Urban Interventions: Using Technology as an Engagement and Idea Inducing Tool

The urban planning discipline is increasingly turning to specialized technologies to better understand the multiple and complex processes within cities. Automation is already reshaping infrastructure and urban ecosystems. This study seeks to reconciliate technological agency and creative research methods by utilising laser scanning technology to increase community participation in planning and speculate about urban possibilities of using walking and pedestrian viewpoints as drivers for urban design. This research employs hybrid methods, on the one hand the simple act of walking and on the other hand visualising the urban space using a 3D laser scanner. This mixed technique makes it possible to increase the perception of individuals with respect to urban space, becoming more aware of it and coming into greater contact with it generating ideas about spaces encountered on the route.

Daria Belkouri, Theodoros Dounas
Digital Hybridities: Theorising the ‘Social’ and the ‘Local’ of Fabrication Technologies in Craft Practice

The digital design research community keeps moving towards increasingly techno-centric spaces. Largely development-focused, the evolution of technology adoption in our sector is often reported from performance and efficiency perspectives, instead of its efficacy – its implementation and adoption in real-world design practices and cultures. In that context, this paper presents a theory framework to investigate the adoption of digital fabrication technology among craft practitioners - emphasising the challenges among craftsperson’s activities protected by both heritage and cultural traditions developed outside authored and institutionalised contexts of digital design research. Through the coupling of theoretical strands originated in management studies (socio-materiality), media obsolescence, heritage, and crafts theory, our approach is demonstrated through the infusion of digital fabrication tools into the analogue world of letterpress printmaking. Through methods such as community engagement, codesign and prototyping, and graphic outputs, we reflect on issues emanating from uniting a technology that has already faced industrial obsolescence with newly developed digital tools, including the influence of heritage and cultural traditions, tensions around irreplaceability, the need for preservation, spatial and community manifestations, and knowledge transfer and translation across seemingly diverging ways of engaging with technology. The resulting approach challenges the standard hegemonic analogue/digital dichotomy and allows for the interrogation of a more ‘complexified’, nuanced field of hybrid practices encouraging a balance between preservation, tradition, and experimentation.

Matthew Holmes, Alejandro Veliz Reyes
Exploring an Evolving Architectural Pedagogy in the Age of Digital Creativity and Artificial Intelligence: Examining the Challenges to Critical Thinking

The advent of digital creativity and artificial intelligence (AI) is rapidly changing the way we think, design and construct architecture. This transformative methodology, must also inevitably lead to a continued evolution in architectural pedagogy. Whilst these new technologies, computational tools and data-driven processes suggest new possibilities for creativity and innovation, there is an inherent perception they may also pose a threat to the development of the traditional design skills within architectural education. This paper seeks to explore the impacts of new ways of design and the importance of retaining creative critical thinking processes in design education.

John Latto
Exploring 3D Concrete Printing of Lattice Structures on Robotically-Shaped Sand Formwork for Circular Futures

This research bypasses the use of wasteful scaffolding and moulds, by exploring 3D concrete printing (3DCP) on reusable sand-based substructures. Non-standard, complex geometries generally require the use of formwork to be produced, leading to wasteful, material-intense manufacturing processes. The research explores optimised material depositing strategies for 3DCP on robotically shaped sand formwork. The need for timber scaffolding, plastic or foam-based moulding for casting concrete is avoided. The fabricated structures are lattice-based lenses with varying curve densities, envisioned as screens part of facade systems and spatial dividers. The research addresses the need for circular construction, reduction of raw-material usage for concrete formwork and the development of optimised material depositing strategies to undercut concrete usage. The deployed method falls under the category of sub-additive concrete printing. Firstly, the sand-based formwork for printing is shaped robotically through the use of different customised end-effectors. The robotic sand-forming of the substructure can be repeated multiple times, as almost no material loss is encountered. Subsequently, the robot arm is used for 3DCP along a three-dimensional tool path on the robotically shaped sand formwork. Parameters such as extrusion flow, printing speed and angle were tested and optimised to guarantee high-precision printing and resolution.

Cristina Nan, Alessio Vigorito
Geometric Variability and Viability in Designing and Fabricating Concrete Façade Components–A Systematic Review

This paper explores the integration challenges of advanced parametric modelling techniques and architectural-scale concrete façade fabrication technologies. Despite concrete’s versatility and durability, which make it a preferred material for parametric façade designs, a nuanced comprehensive understanding of balancing its geometric variability and viability is absent. This review investigates the interplay among digital geometric design and fabrication techniques, shedding light on design strategies regarding fabrication constraints and the limitations of current design approaches. By categorising design methods in concrete façade design and production, it underscores the importance of fabrication-informed parametric design strategies. The paper reviews recent research on geometry types and related design approaches. It concludes by highlighting the strength and potentials of balancing geometric variability and viability in the parametric context, which has implications for the future design and construction of concrete architectural elements.

Deyan Quan, Christiane M. Herr, Davide Lombardi
Augmented LEGO™
An Experiment Utilising Augmented Reality (AR) for Algorithm-Oriented Generative Design and Conceptual Model Assembly Guidance

Using discrete elements, LEGO™ bricks, as the design unit, this paper presents experimental research utilising augmented reality (AR) technology for algorithm-oriented generative design and conceptual model assembly guidance. The research aims to develop a unique pipeline and workflow that allows users to modify, set constraints, preview, generate discrete architectural design outcomes immersively, and assemble the physical conceptual model manually through AR guidance for the initial architectural design draft stages. A sample workflow has been tested as a series of generated conceptual complex discrete structures in the Augmented LEGO™ workshop. We transformed the current design method to an algorithm-oriented way with discrete element generate design plug-in Wasp, and enriched the current generative design, scheme preview, and the handicraft model-making methods holographicly with AR immersion plug-in Fologram. As for the physical outcomes, all participants designed and assembled generated discrete LEGO™ structures successfully with the assistance of AR. To conclude, this paper describes the workshop research questions, methods and process in detail, reflects and summarises the findings and limitations of the Augmented LEGO™ experiment at the end.

Yang Song, Wei Zhao
Virtual Reality and EEG in Creativity Research: Investigating the Impact of Designed Environments on Creative Performance

Creativity is a distinctive feature of human nature that involves various cognitive processes and drives innovation, progress, and personal growth. Recent research in cognitive neuroscience challenges the traditional belief that creativity is a fixed trait. Through investigations of the temporal neural correlations of a person’s creative action, neuroscientists have revealed that creativity is dynamic and based on both explicit and implicit processing to generate and evaluate ideas. In other words, there are distinct steps that lead to a creative action or proposal, such as the analysis of a task, the generation of ideas and their verification, which require different modes of thinking. These different modes of thinking, which correspond to different patterns of brain waves, can be further categorised into divergent, convergent, abstract, and concrete thinking.This paper presents an overview of an ongoing research project that aims to investigate the effect of designed environments on the different stages of a human’s creativity. Tracking the creative performance of individuals in the VR space by using both electroencephalography (EEG) and questionnaires allowed us to gain insights about the ability of spaces with high aesthetic quality to foster creativity. The experimental set-up permitted us also to draw conclusions about the suitability of neuroscience tools in architectural design contexts. This paper provides an overview of the theoretical basis, and a critical review of the employed tools and methods, with a focus on the use of VR technology and EEG in evaluating creativity. Furthermore, the paper outlines potential applications of VR, specifically through VR drawing, in empirical studies of creativity.

Fatemeh Taherysayah, Claudia Westermann
Analysis of Differences in Street Visual Walkability Between Human and Machine Perception: A Case Study of an Anonymous University Campus

Recent studies of street visual perception have shown that street visual walk perception can be predicted using deep learning models, but machine-human perceptual differences limit the direct application of deep learning models to decision aids. In previous research, we developed a visual walk perception classification deep multitask learning (VWPCL) model for measuring visual walk perception (VWP). Also, the activation maps generated by the interpretable machine learning method Grad-CAM (Gradient-weighted Class Activation Mapping) were used to generate visual interpretations for the prediction results of the VWPCL model. However, its visualised machine perception results are not validated with real human visual perception data, and therefore designers have difficulty trusting the model’s perceptual prediction results. Based on this issue, this study conducted an experiment based on a desktop eye-tracker on a university campus to analyse the differences between human and deep learning models in street visual perception. The results of the study show that there are some differences between humans and deep learning models in street vision walkability perception. In future work, more quantitative analysis methods based on image comparisons and other sensory data will be incorporated for further in-depth research.

Yuchen Xie, Yunqin Li, Lingshan Huang, Jiaxin Zhang

AI and Environmental Session

Exploration of Conceptual Design Generation Based on the Deep Learning Model – Discussing the Application of AI Generator to the Preliminary Architectural Design Process

The rapid advancement and heightened awareness of Artificial Intelligence (AI) have stimulated a substantial surge in the growth of deep learning models. This has led to an increasingly prevalent debate surrounding the possibility of AI replacing human architects. Nevertheless, it is foreseeable that architects will explore an AI-aided design process at this stage. Several deep learning models, including NovelAi, DELL-E·2, Midjourney, and Stable Diffusion, have emerged, making it easier to generate images efficiently without the need for multidisciplinary knowledge related to algorithms and programming.During the conceptual design phase of an architectural project, it is crucial for architects to present several massing proposals in various styles within a limited timeframe. It means a huge amount of modelling and drawing works. This paper focuses on Stable Diffusion, Midjourney, and DALL-E 2, as primary examples to discuss the approaches used in the preliminary design process as a smart assistant. These AI platforms are expected to optimize the conceptual design work by reducing the time of transforming hand-drawn sketches into rendering photos and enhancing the visualization of massing diagrams. This article analyzes the impact of AI work-related activities carried out by architects and architectural students based on a designed survey containing various images generated by AI programs. The survey aims to investigate the performance of several popular AI programs and architects’ perspectives towards AI. The findings indicate that AI has the potential to assist human architects to some extent with satisfactory performance. The effective application of AI generators can significantly optimize the design process, allowing architects to explore more creative and aesthetic aspects.

Yuxin Bao, Changying Xiang
The Taste of Textures
Artificial Intelligence Driven Gastronomic Design and Crossmodal Correspondences in Living Art

This research delves into the application of artificial intelligence (AI) in bio-art and gastronomy. It comprises a chapter within a broader interdisciplinary project that aims to create a dynamic, interactive, and multisensory artwork that seamlessly integrates biology, art, computational design, and gastronomy. The project investigates the interaction of microorganisms with various substrates and eco-friendly materials, the role of AI-assisted computational design, and the potential of flavour engineering to enhance the artistic experience. This paper explicitly examines the use of AI-assisted conceptualisation and computational design in generating unique flavour-related textures. Relying on gastrophysics studies, this research incorporates flavours’ objective and subjective properties into the design process. The findings underscore the effectiveness of interdisciplinary collaboration in producing artistic research and fostering innovation. Future research phases will focus on 3D modelling using parametric design and 3D printing the textures on Petri dishes, conducting experiments with microbial populations to form complex patterns and textures based on the initial AI-generated designs, contributing to the evolving nature of the artwork. Furthermore, the study will explore the audience’s engagement in interactive experiences. This study adds to the body of work on AI-driven design for practical and theoretical applications in developing innovative bio-art and gastronomic experiences.

José Antonio Carrillo Andrada, José de la Rosa Morón, José Luis Oliver Ramírez
AI Machine Learning in Creative Architectural Design Processes

An increasing number of designers, architects, and artists are using new technologies and artificial intelligence as mediums, aware of their contemporary relevance. Architectural design is based on technical knowledge, accumulated experience, and an intuitive “creative” component able to express the designer's unique talent. Artificial Intelligence provides suggestions and ideas to designers, acting as a collaborative partner in their creative phase. From this perspective, AI has been identified as a good support, able to suggest ideas during conceptualisation, one of the most critical phases of the Design process. This paper explores the integration of AI and Machine Learning style transfer in architectural education to enhance creativity and design inspiration. It comes as the result of three years of experimentation in an academic environment where Master's students in Architecture have been asked to apply and understand Neural Networks and methods to train them to perform specific given tasks. During the numerous experimentations, an interesting evolution has been observed across the three years when users approached this innovative Design tool in architecture. AI-informed design processes have been a good practice of “learning by doing”, breaking the rule about having just one solution in architectural design processes. Machine Learning applied to creativity requires a correct understanding of the input and a good level of abstraction during the phase of interpreting the results. This paper also aims to inform the audience about the workflow of creative AI applications and the philosophy of “Creating with Artificial Intelligence.”

Juan Carlos Dall’Asta, Giancarlo Di Marco
An Assessment of Thermal Comfort in Urban Quality of Life in Architecture Using Fuzzy Logic in Decision Making: A Case Study of Iran

Thermal comfort is a notion that has been discussed recently in various studies, in particular architecture and urban planning as a response to many problems facing new cities all over the world and it is one of the factors that plays a very important role in the quality of life in architectural and urban design process. Evaluating thermal comfort based on climatic conditions assist architects and designers in choosing suitable regions to shape cities and buildings. In this context, Iran as a country with different climatic conditions is proposed to be analyzed and visualized as a case study. Fuzzy logic approach is used in this study as the methodology in conjunction with its inputs that are defined as air temperature, air quality, and humidity which are known as indispensable principles in architectural and urban design, and the output is determined as thermal comfort in each province, ranges between 0 and 1 (from not preferable to the most preferable provinces). This paper aims to throw light on the importance of fuzzy logic approach in architecture and urban planning and the process of analyzing thermal comfort of each region for users by means of MATLAB (a fuzzy logic-based software). For this, after an introduction and overview on fuzzy logic method and its application in this study, the results of analysis obtained are collected in tables and visualized as figures.

Alireza Gogani, Faezeh Choobkar, Asli Cekmis
A Language Prompt Model for Architectural Aesthetics

Our main concern with AI and architecture is that AI will ultimately mimic what we call creativity even though it remains a black box of the type Banham described [1]. We claim to recognize it when we see it but can’t agree what it is, how it works, how to foster it, or how to teach it. If we believe creativity is the generation of novel shapes, then it won’t make any difference if it’s performed wholly or in part by computation, intern farm or some other means of generating quasi-random permutations. Meanings will still need to be assigned to those shapes and it’s the black box that does that.Any design process produces better results when the instructions are clear. Quickly searching a large image dataset is a computational problem but organizing it and instructing AI to retrieve and synthesize relevant information is an aesthetic one. The author reverse-engineers Charles Jencks’ model of an iconic building into one that also describes (and hence classifies) other aesthetic effects. The names of these effects become language prompts linking the aesthetic problem to the computational one, allowing large image datasets to be consistently indexed and searched, enabling more relevant training, and reducing the need for meanings to be externally assigned.

Graham Brenton McKay
Employing AI-Based Tools to Support Exhibition Design: A Science and Technology Museum Case Study

This paper investigates the potential role of AI (Artificial Intelligence) technology in the design of future-oriented interdisciplinary exhibitions for science and technology museums. With AI leading technological advancements in the field, this paper explores how AI can not only be the subject of exhibitions but also support the design of exhibits. Drawing on applied design experience from an ongoing science museum project in China, central questions for designers and researchers working with AI-based techniques is whether and how such tools can support original design outcomes: Are ideas developed by designers before using AI tools or in the process of AI generation? Can skilled use of AI allow designers to set aside more time for creative ideas, thus enhancing their productivity? We describe in detail the process of exhibition design from the perspective of the exhibit designer, and focus on the dynamics of AI-supported design processes, where schemes are quickly iterated until suitable results are produced for final selection. Finally, we discuss how we have employed the potentials and addressed challenges introduced by creative AI use in our work.

Lulu Pei, Chenxiao Li, Jun Xiao, Yu Zhang, Christiane M. Herr
An AI-Mediated VR Sound Installation

Artificial Intelligence (AI) and Extended Realities (XR) have the potential to create new worlds, new narrative spaces. From our standpoint, to be believable, those worlds need not only to convince our senses, but also our experience reality: a complex, non-linear net of relationships among objects, beings, actions and concepts. In other words, we wanted to create a narrative space rich and complex, in terms of content and behaviour. At times, non-linear and unpredictable.In Oracle, we explored some boundaries of this idea. Oracle is an installation based on a variable chain of spatialized sound processing algorithms directly controlled by a multilayer perceptron neural network (the “oracle”). The sound input of the system is the voice of any participant who wants to play as a “visitor” (the one who poses a question to the oracle). The output will be a processed version of that input, a slight modification, a completely different sound texture or anything in between these extremes. By wearing a VR headset, the visitor can interact with the oracle and influence the output of the neural network, therefore the sound output. However, it is not possible for any of the users to exactly predict the outcome of such interaction. The oracle’s answer is then a net of sound relationships the user needs to decipher, not to get the answer, but to better understand the question.

Giovanni Santini, Zhonghao Chen
Space Narrative: Generating Images and 3D Scenes of Chinese Garden from Text Using Deep Learning

The consistent mapping from poems to paintings is essential for the research and restoration of traditional Chinese gardens. But the lack of firsthand material is a great challenge to the reconstruction work. In this paper, we propose a method to generate garden paintings based on text descriptions using deep learning method. Our image-text pair dataset consists of more than one thousand Ming Dynasty Garden paintings and their inscriptions and postscripts. A latent text-to-image diffusion model learns the mapping from descriptive texts to garden paintings of the Ming Dynasty, and then the text description of Jichang Garden guides the model to generate new garden paintings. The cosine similarity between the guide text and the generated image is the evaluation criterion for the generated images. Our dataset is used to fine-tune the pre-trained diffusion model using Low-Rank Adaptation of Large Language Models (LoRA). We also transformed the generated images into a panorama and created a free-roam scene in Unity 3D. Our post-trained model is capable of generating garden images in the style of Ming Dynasty landscape paintings based on textual descriptions. The generated images are compatible with three-dimensional presentation in Unity 3D.

Jiaxi Shi, Hao Hua
Strategies of Interconnecting Deep Learning Models in AI-Driven Design Systems

Incorporating deep learning (DL) models into architectural design presents challenges, despite the potential to inform new design processes. Developing DL-driven systems requires identifying components and relationships between these constituents in the new design workflow. The study tests a novel DL-driven design workflow, employing systems theory to deconstruct the design process into its component parts. The proposed workflow considers design an “exploratory activity” involving the modification and evolution of problem goals and methods used to achieve those goals and determine the types of connections and combinations of those connections. DL model connections tested here involve sequential, parallel, branching, with designers choreographing the interaction between human agents and DL agents. The research involves testing the proposed workflow prototype through three case studies of different strategies. Evaluation of those work-flow strategies was performed through the linkography method, to assess how different connection strategies yield different processes. The study's significance lies in crafting “hybrid” processes that leverage human intuition and machine intelligence, yielding a creative state when the design space becomes ever-changing, in a process that unfolds new possibilities of design exploration.

Shermeen Yousif, Daniel Bolojan
Meta-morphing Architectural Domains: The Role of Humans and AI in Post-human Architecture

Throughout history, the practice of architecture has been centered on fulfilling human needs and aspirations. The emergence of post-humanism challenges these conventional boundaries and foci, expanding design thinking by recognizing humans as one element amongst a multiplicity in the design environment, offering opportunities, relationships, and inclusion for others, including emerging technologies like artificial intelligence (AI).This paper explores the transformative potential of AI in architecture within the context of post-humanism. This research aimed to determine the roles of human and artificial intelligence in the architectural design paradigm, particularly within a context of coexisting parallel intelligences. Our focus has been on spatial floor layout generation within a fixed design scope.

Asif Hasan Zeshan, Susannah Dickinson
Optimization and Design of Building-Integrated Photovoltaic Systems for a High-Rise Building in Shenzhen

Cities with large populations and limited space, such as Shenzhen, China, require innovative approaches to distributed photovoltaic (PV) power generation on building surfaces to meet renewable energy production goals. Despite the city's subtropical climate and abundant solar energy resources, along with numerous buildings with potential for PV power generation, architects remain cautious about adopting extensive PV panels on the facades of high-rise buildings. This paper addresses this challenge by integrating engineering and design considerations to facilitate future sustainable design transitions. To achieve optimized Building-integrated Photovoltaics (BIPV) in Shenzhen, a case study building is utilized to identify the most suitable PV materials with optimized power generation efficiency, considering solar energy availability and geographical location. The Grasshopper platform, a graphical algorithm editor integrated with the Rhinoceros 3D modeling software package, and PVSyst are employed to determine the angle of solar panels and the physical arrangement of PV modules through building shape modeling and optimization techniques. Four different angles (18°, 45°, 60°, and 90°) of PV module layouts are designed, and simulation results demonstrate their impact on electricity generation efficiency. Notably, a vertical arrangement (90°) of photovoltaic components on the building facade significantly reduces electricity generation efficiency. The proposed simulation method optimizes building PV systems while considering power generation efficiency and supports the future design of energy-efficient residential and office buildings in Shenzhen, supporting long-term reductions in carbon emissions.

Yuqi Zhang, Christiane M. Herr, Yongcong Guo
Structuring Gamified Participatory Public Space Design Developing a Design Quality Evaluation System to Support Digital Co-creation Processes

Participation and co-creation are increasingly used to incorporate end-users’ demands and mitigate conflicts of interest. Digitalised games are introduced to better visualise design scenarios and invite multiplayer collaboration. A recurring problem is how much input and guidance are needed to achieve creative and feasible outcomes. This paper explores how guided forms of gameplay can lead to more informed negotiation and better game outcomes. The study focuses on public space design in a high-density housing estate, where widely varied resident demands put pressure on limited space. The methodology employed in this study involved the development of a design quality evaluation system to support participatory processes. To recruit study participants, design students were selected from the same course and randomly assigned into teams. These participants were then engaged in co-creation using a digital sandbox game that was designed to facilitate the process. Participants’ co-creation outcomes were analysed through a combination of qualitative and quantitative methods. The original contribution of this study lies in the development of a user-activity-based toolkit for spatial configuration analysis. Preliminary results demonstrate how structuring collective design explorations around principles of activity complexity, sociability, environment comfort, adaptability, surveillance, and wayfinding can offer a more objective basis for collaboration. The implications of this approach can activate collective creativity in the age of digital production and contribute to the creation of more inclusive and user-centric public spaces.

Shutong Zhu, Provides Ng, Jeroen van Ameijde
Creativity in the Age of Digital Reproduction
Giancarlo Di Marco
Davide Lombardi
Mia Tedjosaputro
Copyright Year
Springer Nature Singapore
Electronic ISBN
Print ISBN