This paper introduces a study demonstrating the growth of plants robotically, where robots live on the stem of a plant and morph their growth without external artificial scaffolding. The encoded software in the robot maintains interval locomotion over twelve weeks, while triggering on board lighting climbs to direct the growth. Outputs of twelve weeks of growth experiments in total are presented with the final shapes of plants. We also discuss the morphogenetic plasticity of plants and their growth responses to the environment, and other mechanisms of shaping that could be used in the future. Such work may pave a way towards new forms of arbortecture in the future.

Machine Learning (ML) in architecture is an emerging field with myriad potentials to impact the design process. Despite its many possibilities, ML is typically employed when the design problem is sufficiently defined, and further, is only integrated within software environments. Desk Mate is collaborative drawing machine that can be used early in the design process by coupling tangible tools like pens and trace paper with ML driven feedback and generation. Embedding physical tools that are familiar and intuitive with digital intelligence offers designers new ways of engaging with ML algorithms interactively, potentially changing the way the architectural industry approaches design problems. Desk Mate chains together image retrieval methods from machine vision with generative ML models like variational autoencoders (VAE) and generative adversarial networks (GANS) to react to design sketches as they are drawn. This pipeline allows Desk Mate to iterate through designs with the designer. Thus, Desk Mate demonstrates an interactive platform that collocates designer and machine as creative agents, facilitating drawing with ML driven feedback, potentially accelerating design iteration in the early stages of ideation.

The larger visual identity of a city is often a blend of smaller and distinct visual character zones. Despite the recent popularity of street-view imagery for visual analytics, its role in uncovering such urban visual clusters has been fairly limited. Taking Mumbai as a demonstrative case, we present what is arguably the first city-wide visual cluster analysis of an Indian metropolis. We use a Dense Prediction Transformer (DPT) for semantic segmentation of over 28000 Google Street View (GSV) images collected from over 7000 locations across the city. Unsupervised k-means clustering is carried out on the extracted semantic features (such as greenery, sky-view, built-density etc.) for the identification of distinct urban visual typologies. Through iterative analysis, 7 key visual clusters are identified, and Principal Component Analysis (PCA) is used to visualize the variance across them. The feature distributions of each cluster are then qualitatively and quantitatively analysed in order to examine their unique visual configurations. Spatial distributions of the clusters are visualized as well, thus mapping out the different ‘faces’ of the city. It is hoped that the methodology outlined in this work serves as a base for similar cluster-based inquiries into the visual dimension of other cities across the globe.

The labour shortage is impacting the construction industry globally, and 3D concrete printing (3DCP) technology is considered a solution for such an issue by using robots instead of manpower in building construction. However, due to the unstable mechanical properties of the fresh-state concrete, current 3DCP building forms exclude a massive number of options, one of them being the overhang shape. Therefore, this paper introduces bionic wrinkles to improve the overhang of 3DCP shell prototypes and demonstrates the feasibility of this idea through three groups of buckling simulations. This study proves that surface wrinkles can improve the in-process mechanical properties as well as the overhang capacity of shell structures. In the best scenario, the original design which only reached 30° overhang can be promoted to 77.5°. Besides, the applications of all wrinkle types are robust.

Being immersive online and physically isolated during the COVID-19 pandemic may not be the future of the metaverse we anticipate. Therefore, the rising challenge of creating metaverses does not lie in what novel virtual experiences can be offered but in how to make the experience more meaningful to users. This involves creating an engaging environment for both physical and virtual social interactions and providing equity for a wide range of users. Metaverse Magnifique intends to explore the design of a meaningful metaverse beyond the computer screen. It investigates a combination of the best features of digital and physical environments with human interactions seamlessly conducted and transitioned between the two worlds while also inquiring a better understanding of the changing social norms from fundamental human activities. A series of experimental Proto-metaverse projects based on a critical review of the Metaverse typology are proposed then developed into small-scale designs to highlight a meaningful behavior, action, task, or activity. The projects are then coupled with a physical site and extended into a full-fledged metaverse project integrated within the city. The projects showcase meaningful experiences by translating visual and spatial elements then enabling AI assistive features for better communication or interpretation of subtle interaction nuances.

Urban vitality is the driving force behind sustainable urban development. As the most frequently used public space in cities, the enhancement of street vitality is of great significance for improving human-centred habitats. Based on multi-source big data, this study uses spatial and statistical analysis methods to explore the impact factors of street vitality. Through the quantitative evaluation of these factors, we propose corresponding strategies to enhance the vitality of the street. Firstly, the spatial elements of streets are extracted using deep learning algorithm based on the acquired street view images. Further, the impact factors of street vitality are demonstrated using statistical methods by combining multi-source data. We established an evaluation system based on the impact factors of street vitality, which can quantify and predict street vitality. In this way, we can propose vitality enhancement strategy for the street with lower vitality in a targeted approach. The feasibility of the process is demonstrated by using Ding Shu as an example. This study provides a basic framework for a people-centred approach to enhance street vitality based on big data. It also contributes to causal inference in urban problems.

Through 3D printing of a mixture of clay and natural fibres, this paper proposes a first design experimentation to understand the parameters that influence mycelium materials' growth, including inoculation (IS) and fabrication strategies (FS). Given the broad spectrum of complex, interrelated variables, the aim is to provide insight based on many empirical experiments and visual inspection through a series of prototypes. The growth behaviour of mycelium and the visual inspection highlight that the inoculation strategy with a post-inoculation of mycelium in the substrate is the one that assures maximal mycelium colonization. Through empirical testing, we demonstrated control over the growth process by guiding the manual insertion of mycelium spawn with undulated areas on the printed surface generated through an image sampling algorithm. Moreover, such a strategy is viable for future programmed growth artefacts once the interactive insertion of mycelium spawn is substituted with a multi-material technique allowing for controlled growth in selective areas induced by the fabrication technique.  In terms of resource optimization, the FS that optimizes the use of the material is the most favourable since it was possible to obtain the same final colonized geometry with less material.

From the perspective of human-centered urban planning, walkability is a crucial concept for enhancing the quality of the neighborhood environment experienced in day-to-day life. Commercial facilities have the greatest impact on a walkable neighborhood environment. However, few studies analyzed the walkable environment's characteristics in consideration of local businesses' economic growth. This study aims to classify commercial areas according to vitality level and to analyze the correlation between store density and walkability factors through a case study on Seongsu district, Seoul, a commercial district where small businesses are growing. First, a Geographic Information System (GIS) based hotspot analysis is performed using the commercial area vitality index to select a target area for the case study. Second, through the Seongsu district case study, the walkability features of the cluster at the street level are evaluated and compared based on 3D (density, diversity, design). The results show that store density is correlated with walkability factors in growing commercial areas, and that there are distinct spatial differences depending on the factors. Based on this study's results, it is possible to propose a combination of a multi-use main street, a commercial street close to life, and a specialized street adjacent to green spaces.

The subject of this research is the study of the retraction change mode of deployable scissor grids based on the Hoberman mechanism. The retraction logic of this type of flat mechanism can be changed mainly by moving the pivot point of the rod and using bistable deployable scissor structures consisting of translational units. Therefore, the mechanism can remain flat while it retracts, and the irregular translational units allow for a greater variety of surface variations in the shape of the mechanism. Through the study of the scissor system, a simplified mathematical model is used to explore the geometric potential, and a formula for complete flat retraction is derived. Following the input of defined data using digital tools, the remaining translational scissor units that conform to the retraction logic are generated. Then, irregular linkage mechanisms are created that can retract from 3D to 2D, with the opening mode not being limited to the radial sphere or other mean geometries. These results provide a unique retraction mode for deployable scissor grids, thus facilitating the collection and transportation of such mechanisms in practical applications.

Urban planning often overlooks the diversity of plant species and the perspectives of pedestrians. This study introduces the View Index of Plants of Interest (VIPI) as a new index for evaluating street plants from a pedestrian perspective. VIPI uses image classification and semantic segmentation techniques and was applied to four popular ornamental street plants: cherry trees, maple trees, magnolia trees, and ginkgo trees. The model used achieved a high level of accuracy with a mean intersection over union (mIoU) of 81.06. And the VIPI satisfaction criteria were used to evaluate several cases. The results provide valuable insights for urban planners and policymakers, allowing for a more detailed and accurate evaluation of urban plants from a pedestrian perspective and can guide urban greening actions. Additionally, this study demonstrates the potential of utilizing computer science techniques to inform urban planning and design decisions.

BridgeSlicer is a design tool and a workflow for FDM (Fused Depositing Modelling) 3D printing to create perforated shells using bridging. Bridging is a known 3D printing technique in which the printed material is extruded and pulled in mid-air between raised geometries. Our design tool allows users to use bridging to creatively incorporate perforation patterns into 3D models by modifying the toolpath rather than the geometry of the 3D file. Users may control the hole patterns parameters like hole size, shape, density, direction, and flow. Our workflow enhances the functionality of 3D-printed objects by improving strength-to-weight ratio and by introducing transparency, breathability, and flexibility. Additionally, it allows the printing of thin hair-line features and structures with many holes, that are challenging to print using the standard workflow. BridgeSlicer is demonstrated with a series of 3D printed samples and large-scale functional applications such as a chair seat and lampshades.

In line with the 2023 CAADRIA conference theme, Human-Centric, this research aims to promote cultural and societal shifts towards climate justice, and equitable approaches to sustainability, by promoting the use of natural systems and locally sourced, upcycled materials in the design and making of architectural systems. This research paper and project, titled Hybrid Bio-Based Architectural Systems, explores possibilities for designing and fabricating architectural systems that merge living organisms, upcycled waste, and digital technologies. The paper focuses on three living organisms; fungi, algae, and bacteria, and the use of upcycled waste materials as substrates for growing mycelium, the vegetative part of fungi. Through a series of physical experiments and prototypes, new hybrid models of living and non-living materials are formulated as extrudable pastes for 3D printing and robotic deposition. Each 3D printed component, which aggregate to form a larger assembly, is inoculated and grown with mycelium. The research reframes concepts of ecological design, as collaborations with living organisms, and symbiotic relationships between human and non-human species, that challenges traditional and conventional notions of designing and making architecture in the post-Anthropocentric era.

Recent advances in Natural Language Processing (NLP) and Diffusion Models (DMs) are leading to a significant change in the way architecture is conceived. With capabilities that surpass those of current generative models, it is now possible to produce an unlimited number of high-quality images (Dhariwal and Nichol 2021). This opens up new opportunities for using synthetic images and marks a new phase in the creation of multimodal 3D forms, central to architectural concept design stages. Presented here are three methodologies of generation of meaningful 2D and 3D designs, merging text-to-image diffusion models Stable Diffusion, and DALL-E 2 with computational methods. These allow designers to intuitively navigate through a multimodal feedback loop of information originating from language and aided by artificial intelligence tools. This paper contributes to our understanding of machine-augmented design processes and the importance of intuitive user interfaces (UI) in enabling new dialogues between humans and machines. Through the creation of a prototype of an accessible UI, this exchange of information can empower designers, build trust in these tools, and increase control over the design process.

Cities globally are adopting “The 15-Minute City” as an urban response to various crises, including the Covid-19 Pandemic and climate change. However, the challenge of linking location-specific requirements with potential design solutions hinders its effective implementation. To bridge this gap, this paper introduces a novel urban 15 Minute City concept generation tool that applies an artificial intelligence (AI) method called a pre-trained language model (PLM). The PLM model was fine-tuned with structured examples based on 15-Minute City principles. Using a PLM, the tool maps 15-Minute City concepts to a location and project specific prompt, automatically generating neighbourhood design concepts in the form of natural language.

This paper responds to a gap observed between the contemporary capacity for calculation and analysis of visibility of built environment features, such as buildings, in digital urban and architectural computational research models and the functionality of off-the-shelf software tools available to professionals. The research investigates the potential of visibility analysis to be embedded and extended within computational-based workflows of software tools to better meet urban design and planning industry needs. We introduce a novel method for visibility calculation that exposes output data for further analysis within a computational workflow and implement it in a game development engine used by software tool providers. Based in our engagement with a local government authority, we then use that method to demonstrate a workflow in the context of form-based building codes in which the visual impact of a building is considered rather than prescriptive limits on dimensions and use. Our results indicate the novel method has substantial performance improvements compared to an alternative mode of visibility calculation and that software providers could more thoroughly integrate and extend visibility analysis to meet industry needs.

This ongoing research explores the opportunities of Polyvinyl Alcohol (PVA) as a reusable water-soluble 3D printed formwork for more circular and complex concrete casting. The paper first explores the feasibility of reusing PVA by discussing the various methods of expediting its dissolution process, harvesting, and dehydrating the material for recycling. Next, a fabrication case study of a partial vault structure is introduced to explore the added structural complexity and material optimization enabled by the water-soluble 3D printed formwork and finite element analysis methods. A series of block designs were tested with an Instron 5566 Universal Testing Machine with a 10 kN load cell. The compression testing demonstrated that the integration of reinforcement and certain design choices were effective. The results point to future research that may reduce the embodied carbon emissions of concrete casting through formwork recycling and material optimization.

Machine learning has been proven to be a very efficient tool in urban analysis, using models trained with big data. We have seen research that applies a generative adversarial network (GAN) to train models, feeding the street map and visualized urban characteristics to predict certain urban features. However, in most cases, the input map is a two-dimensional (2D) map that only stores the land type data (e.g., building, street, green space), hence reducing building information to only the ground-floor area. The identities of buildings with similar floor areas can be hugely different, which may contribute to the prediction errors in previous machine-learning models. In this research, we emphasize the importance of the use of an image-based neural network to analyze the relationship between urban features and the constructed environment. We compare the model that uses traditional street color maps as the input set, against a new input set with more detailed building data. Once trained, the model with the enhanced input set yields output at a higher level of accuracy in certain areas. We apply the new model framework to three selected urban features predictions: rental price, building energy cost, and food sanitary ratio. A broad range of new research could be conduct with our new framework.

Using building information modeling (BIM), design teams can maximize decision-making efficiency by using one data-sharing platform and one integrated digital model. We present a novel built-project that integrates computer-aided manufacturing (CAM), machine learning, and internet of things (IoT) with a BIM process. The goal is to solve design and manufacturing problems and tightly connect virtual design data with the real-world construction process. Introducing CAM in the early phase reduces the cost of reverse engineering and optimizes material and construction costs. Machine learning has been used for curtain wall panel standardization and to solve manufacturing problems. The IoT concept focuses on directing the data stream onto real-world objects and updating the digital model using feedback from real-world monitoring. Using the integrated application in this project, a hybrid Olympic stadium, helped to accelerate the process of design and reduced the time and cost for manufacturing and construction.

Our paper demonstrates a computational design workflow that creates and maps optimal 2D strut layouts based on input 3D shell geometries that function as membrane tensegrity shell (MTS) structures suitable for human occupancy. This workflow links conformal mapping, structural analysis, and optimisation algorithms to iterate through a series of strut layout parameters. From these layouts, we generate digital MTS models that, under structural loading, closely match their respective target models. We validate this workflow across five different geometries and this has produced low average local deviations that range between 47 to 65 mm, proving that our workflow is viable for non-standardised wide-spanning (8.0m) shell geometries with openings.

This research investigates a method of urban building energy simulation (UBES) by integrating Building Information Modeling (BIM), building simulation, and algorithm-based prediction to forecast the impact of surrounding conditions. In the urban context, building energy performances are determined not only by the individual building design but also by the building's surrounding context. Many energy performances are sensitive to outdoor and surrounding building conditions, such as neighbouring building volumes, heights, and spaces between buildings. However, such surrounding conditions were overlooked because they can exponentially increase the complexity of urban modeling and simulation. In that regard, the research sought to investigate a novel framework to take advantage of accurate performance simulations and algorithm-based fast predictions. This paper presents our UBES method implemented from three research phases: (i) building a parametric urban model in BIM to provide simulation inputs, (ii) creating a parametric simulation interface to produce training and validation data, and (iii) creating a prediction interface using a Support Vector Machine (SVR) algorithm. Lastly, the paper elaborates on the findings from the prediction results.

The advancing digitalization in the building sector with the possibility to store and retrieve large amounts of data has the potential to digitally support planners with extensive design and construction information. Large amounts of semi-structured three-dimensional geometric data of buildings are usually available today, but the topological relationships are rarely explicitly described and thus not directly usable with computational methods of AI. To this end, we propose methods for indexing spatial configurations inspired by the similarity analysis of incomplete human fingerprints, since the early design stage of architectural design is characterized by incomplete information. For this, the topology of spatial configurations is extracted from Building Information Modelling (BIM) data and represented as graphs. In this paper, Semantic Building Fingerprints (SBFs) and Semantic Urban Fingerprints (SUFs), as well as use cases for AI methods are described.

Additive Manufacturing (AM) for large format building components is becoming popular.  AM has allowed architects and engineers to rethink the process of manufacturing building components through lightweighting strategies associated with the processes of AM. AM allows just-in-time production of components which reduces the need for large storage space and minimizes the carbon footprint of the supply chain by bringing the production closer to the actual construction site. However, the feasibility and efficiency of large format fused filament fabrication (FFF) for large building components are still unclear. This paper presents a Computational Design for Additive Manufacturing (CDfAM) workflow of a doubly curved gyroid lattice wall as part of the research on the technological affordance of large format planar FFF for a doubly curved gyroid lattice wall and the feasibility of 3D printing without support structures.

Example-guided facade synthesis aims to synthesize realistic facade images from semantic labels drawn by architects and example images of user preferences. The automated synthesis approach allows for the efficient generation of facade solutions that will facilitate effective communication between stakeholders and creative inspiration for architects. This study proposes a conditional generation adversarial network with style consistency to solve the problem of example-guided image synthesis. Specifically, the synthesis model is divided into two stages: first, the domain of the semantic label map is transferred to the domain of the realistic image using the pix2pixHD framework to ensure that the synthesized facade in the intermediate stage can be semantically consistent with the designed facade; Second, we use the Deep Photo Style Transfer (DPST) framework to faithfully move the implied features of the realistic facade image synthesized in the previous step to the domain of the provided example to ensure consistency of style. In summary, the proposed method can constrain the synthesis of new residential facades from the semantic labels and example styles. The synthesized residential facades can be consistent with the example styles provided by the client while matching the semantic labels of the facade created by the designer, producing satisfyingly realistic transitions in various cases.

As mass timber construction has become increasingly ubiquitous, doubly curved glued laminated timber (glulam) grid shell structures have challenged standard methods of glulam manufacturing which rely on a wasteful process of planing dimensional lumber into thin lamellas for lamination. The resulting glulam blanks are either milled or cut into doubly curved glulam blanks thereby discarding even more material. Instead of using dimensional lumber to manufacture doubly curved glulam and cross-laminated timber (CLT) blanks, Twistedlam is a robotic fabrication method that intervenes in the glulam and CLT manufacturing process at the sawmill stage, to cut sets of doubly curved boards from a log with a 6-axis robotic arm and bandsaw end effector. The boards were laminated into two hyperbolic paraboloid prototypes: a doubly curved glulam column and a doubly curved CLT blank. Through the construction of these two prototypes, the method not only reduces the amount of discarded material but also simplifies the lamination of the process by eliminating the spring-back produced from twisting flat boards into doubly curved boards for lamination of doubly curved glulam and CLT blanks.

Parametric analysis is emerging as an important approach to building performance evaluation in architectural practice. Since architectural performance has many competing metrics multi-criteria analysis is required to deal effectively with the complexity. However, multi-criteria parametric analysis involves large design spaces that are expensive to compute. Machine learning is emerging as an important design space reduction method for multi-criteria analysis. However, there are many types of machine learning algorithms and architects can benefit from understanding which algorithms perform well on which tasks. Using a mid-rise commercial residential tower project this paper investigates three common machine learning algorithms for performance against three common performance metrics. The algorithms are multi-layer perceptrons, support vector machines, and random forests, while the metrics are site energy, illuminance, and a value function that combines them both. In addition, we seek to understand what factors are most impactful in improving algorithm performance. We investigate four impact factors namely sample size, sensitivity analysis, feature selection, and hyperparameters. We find that multi-layer perceptrons perform best for all three performance metrics. We also find that hyperparameter tuning is the most impactful factor affecting multi-layer perceptron performance.

Elevated pedestrian systems can increase urban density and reduce congestion in urban spaces, which contributes to the sustainability of cities. In high-density cities such as Hong Kong, the complex system of underground passages and skywalks at multiple levels is crucial in facilitating efficient pedestrian circulation. While the relationship between street environments and pedestrian experience has been widely discussed, research on how the perceptual qualities of skywalk environments affect pedestrians’ walking preferences has not yet been addressed. This study demonstrates how the perceptual environmental features of skyway systems can be characterised in a quantitative and human-centric manner. Taking Central, Hong Kong, as a case study, it has investigated the walking environment of the skyway system and the environmental differences between skyways and sidewalks and has explored the relationships between subjective /objective street qualities and pedestrian’s perception. An improved understanding of the environment-behaviour relationships of these spaces can provide suggestions for designing more walkable and comfortable skyway systems that are better integrated in the fabric of the city.

In Hong Kong, the Hakka settlements are the home of indigenous people who have been involved in agriculture and fishing for over 200 years, which has a special place in Hong Kong’s history. However, these settlements are gradually being abandoned as ghost towns due to rapid urbanisation, where the city is progressively constructing high-density habitats to accommodate the exponentially increased population since the 1950s. This challenges designers to rethink means of preserving urban cultural heritage, while engaging in continuous urban regeneration processes. This study investigates workflows to detect historical building styles in one of the most densely-populated cities in the world - Hong Kong - that further deployed in human-computer interfaces in the virtual reality (VR) environment as a collaborative and suggestive design decision-making tool and co-design engagement tool for style infilling on urban regeneration to maintain urban culture inheritance. The workflow aims to discuss the preservation of historical buildings in the context of urban regeneration, urban cultural inheritance through digital archiving, bottom-up community engagement and education in urban design. This study discusses the impact of emerging technologies on the making of communities in human-centric discourse, rethinking social power and the right to the city in participatory mechanisms.

This study uses social network analysis (SNA) to explore the academic development of the CAADRIA research group, and evaluate their influence on the academic circle from an dynamic co-author publication network map. We use mediational centrality to reconstruct the WoCAD (Web of CAADRIA) ontology model, which is based on degree centrality, mediational centrality, and feature vector centrality. This model can help us find: (1) the most influential authors and works, (2) the main participants in the group, (3) the classification of academic researchers in the same group, and (4) the development context and trends of academic researchers, assisting organizers in investigating these academic contents.

Customization has become a vital part of the post-industrial production model. Traditional production methods struggle with the challenge of collecting large amounts of data and the high costs of customization. With advancements in big data and deep learning algorithms, it is now possible to reduce the difficulty and cost of data collection, resulting in more accurate individual customization. This paper presents a proposed workflow for customizing multi-position seating for individuals. Using deep learning algorithms such as OpenPose and parametric design platforms such as Grasshopper, the workflow transforms user-generated photos of the body into a seating model that fits corresponding positions. This process combines deep learning algorithms, simplifies the data collection and processing process, and provides an interface for user interaction on the Grasshopper platform. The workflow provides a comprehensive example of data-driven customization in the context of big data. It explores the potential of a new paradigm in digital design where data is the primary driving force.

In the last few years, digital innovations such as AR, VR and sensing technologies have had a great impact in the sector of cultural heritage, offering new immersive standardized experiences to their visitors. Following this observation, this paper seeks to bring into light the theoretical background and research methodology of ‘Chroma’, a project that lies at the intersection of theories and empirical observations related to color, architecture, human - centric AR and human behaviour in a monument in Chania, Greece. Based on the hypothesis that color has the ability to alter spatial experience, and that different sound frequencies can intensify this experience, the paper aims at testing AR as a possible technology to study different sensual experiences in the monument, measure them and categorize them according to their emotional and cognitive impact. Thus, it builds on a methodology of work where a vast number of different colors and their combinations integrated in an AR app enables users to generate data at a conscious and subconscious level on a suggested site and becomes ground for further exploration.

This paper presents a comparative analysis between a physical model, a set of virtual reality (VR) models and a set of augmented reality (AR) models of the same architectural project. A set of architectural participants’ interactions with the models have been recorded through a set of sensor streams and videos and their experiences have been interpreted through a questionnaire containing both qualitative and quantitative questions. Further analysing through the sensor streams, video recording and questionnaire, their experiences have been interpreted using a framework of embodiment, affordance and tactility to determine the usefulness and limitations and each of the modes and their possible application in architectural design practice.

This study of traditional village morphology provides a possible entry point for understanding the growth patterns of settlements for sustainable development. This study proposes a hybrid data-driven approach to support quantitative morphological descriptions and to further morphology-related studies using open-source map data and deep learning approaches. We construct a dataset of 6819 traditional villages on the Chinese official list with geometrical, geographic and related no-material information. The images containing village buildings combined with roads or other environments are represented in binary to explore the integrated influence of these elements. The neural network is implemented to quantify the morphological features into feature vectors. After dimension reduction, cluster analysis is conducted by calculating the distance between the feature vectors to reveal five main types of Chinese traditional village patterns. The proposed method considers their overall spatial form and other factors such as size, transportation, graphical structure, and density. At the same time, it explores a framework using machine learning in the conservation and renewal work. And it also shows the possibility of data-driven methods for design and decision making.

This paper presents an innovative approach to optimize daylighting in high-rise office buildings, through parametric analysis of dynamic shading system designs. This study concentrates on a kinetic shading angle optimization plot to determine the optimum angles of the dynamic horizontal louver shading systems at specific times with integrated operationalization equations and parametric performance simulations. Solar irradiance and daylighting were considered as performance metrics in this research, which investigated the integration process using the operationalization method in order to find an optimal rotational angle of dynamic horizontal louver shading systems at the specified time. In this study, dynamic horizontal louver shading systems were positioned in different orientations (Southeast and Southwest) to evaluate the effect of the shading’s tilt angles on daylighting. To quantify the daylight quality, maximum and average illuminance were obtained from the raw illuminance on the work plane. At the end, the outcomes of the analyses as well as the optimized angle of the dynamic louver shading were compared to a base case with no shading, and the results prove that dynamic louver with the support of an operationalization method to find optimum angle and testing with parametric performance software leads to optimizing the daylighting performance, enhancing it by approximately 14%.

The balance between energy consumption and indoor environmental comfort is a continuing research topic in building energy efficiency. The dynamic façades (DF) are considered a practical approach to separate the sun and create more shadows for buildings with curtain walls, reducing the HVAC system's energy consumption. However, the design complexity of the DF leads to a time-consuming simulation process, making it difficult to modify the design parameters in the early design stage efficiently. This paper provides optimized control strategies for four dynamic façade prototypes. We use explainable machine learning to explore the relationship between design parameters of DF and indoor performance, including Energy Use Intensity (EUI) and Daylight Glare Probability (DGP). We deployed the trained model in optimizing the rotation angle of DF per hour on a typical day to minimize the EUI and DGP of the target room. The results show that the rotation angle of DF significantly affects the DGP, whereas the room size affects EUI performance more than rotation angles. Optimized control strategies of DF bring a maxim 13.5% EUI decrease and 51.7% reduction of DGP. Our work provides a generalizable design flow for performance-driven dynamic skin design.

Planetary scale computation is evolving the way we digitize the physical urban space. The following research aims to provide an architectural response to the accelerating digitization of our physical world and societal life processes of economy and communications. It acknowledges the legitimate bias in the perceptual value of territories favored by the new Attention Economy of the Metaverse and Blockchain-based Virtual Environments. It proposes the analogy of a theme park derived from the distorted collective vision of today’s reality, of a reduced collection of favored attraction locations. The research provides first a review of contemporary studies related to the operation of the Attention Economy in the Metaverse, Web3 platforms, and Gamified Virtual Environments, as well as studies on recent architectural expressions or typologies of these spaces. A series of methodologies are described next to convey the impact of recent advances in Artificial Intelligence (AI) on the creation of digital personas and worldmaking for this type of economy. The methodologies comprise a three-stage workflow based on data mining and curation, processing through AI-aided generative methods, and implementation with game engine environments, ultimately discussed regarding simulation and creative agency.