ai辅助城市设计

This chapter presents methodological reflections on the necessity and utility of artificial intelligence in generative design. Specifically, the chapter discusses how generative design processes can be augmented by AI to deliver in terms of a few outcomes of interest or performance indicators while dealing with hundreds or thousands of small decisions. The core of the performance-based generative design paradigm is about making statistical or simulation-driven associations between these choices and consequences for mapping and navigating such a complex decision space. This chapter will discuss promising directions in Artificial Intelligence for augmenting decision-making processes in architectural design for mapping and navigating complex design spaces.

Ensuring liveability and comfort is one of the fundamental objectives of urban planning. Numerous studies have employed computational methods to assess and quantify factors related to urban comfort such as greenery coverage, thermal comfort, and walkability. However, a clear definition of urban comfort and its comprehensive evaluation framework remain elusive. Our research explores the theoretical interpretations and methodologies for assessing urban comfort within digital planning, emphasising three key dimensions: multidimensional analysis, data support, and AI assistance.

Urban regeneration presents significant challenges within the context of urbanization, requiring adaptive approaches to tackle evolving needs. Leveraging advancements in large language models (LLMs), we propose Cyclical Urban Planning (CUP), a new paradigm that continuously generates, evaluates, and refines urban plans in a closed-loop. Specifically, our multi-agent LLM-based framework consists of three key components: (1) Planning, where LLM agents generate and refine urban plans based on contextual data; (2) Living, where agents simulate the behaviors and interactions of residents, modeling life in the urban environment; and (3) Judging, which involves evaluating plan effectiveness and providing iterative feedback for improvement. The cyclical process enables a dynamic and responsive planning approach. Experiments on the real-world dataset demonstrate the effectiveness of our framework as a continuous and adaptive planning process.

Can we improve the modeling of urban land surface processes with machine learning (ML)? A prior comparison of urban land surface models (ULSMs) found that no single model is 'best' at predicting all common surface fluxes. Here, we develop an urban neural network (UNN) trained on the mean predicted fluxes from 22 ULSMs at one site. The UNN emulates the mean output of ULSMs accurately. When compared to a reference ULSM (Town Energy Balance; TEB), the UNN has greater accuracy relative to flux observations, less computational cost, and requires fewer input parameters. When coupled to the Weather Research Forecasting (WRF) model using TensorFlow bindings, WRF-UNN is stable and more accurate than the reference WRF-TEB. Although the application is currently constrained by the training data (1 site), we show a novel approach to improve the modeling of surface fluxes by combining the strengths of several ULSMs into one using ML.

The two fields of urban planning and artificial intelligence (AI) arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit from the advances of the other. In the present paper, we introduce the importance of urban planning from the sustainability, living, economic, disaster, and environmental perspectives. We review the fundamental concepts of urban planning and relate these concepts to crucial open problems of machine learning, including adversarial learning, generative neural networks, deep encoder-decoder networks, conversational AI, and geospatial and temporal machine learning, thereby assaying how AI can contribute to modern urban planning. Thus, a central problem is automated land-use configuration, which is formulated as the generation of land uses and building configuration for a target area from surrounding geospatial, human mobility, social media, environment, and economic activities. Finally, we delineate some implications of AI for urban planning and propose key research areas at the intersection of both topics.

Urban Artificial Intelligence (Urban AI) has advanced human-centered urban tasks such as perception prediction and human dynamics. Large Language Models (LLMs) can integrate multimodal inputs to address heterogeneous data in complex urban systems but often underperform on domain-specific tasks. Urban-MAS, an LLM-based Multi-Agent System (MAS) framework, is introduced for human-centered urban prediction under zero-shot settings. It includes three agent types: Predictive Factor Guidance Agents, which prioritize key predictive factors to guide knowledge extraction and enhance the effectiveness of compressed urban knowledge in LLMs; Reliable UrbanInfo Extraction Agents, which improve robustness by comparing multiple outputs, validating consistency, and re-extracting when conflicts occur; and Multi-UrbanInfo Inference Agents, which integrate extracted multi-source information across dimensions for prediction. Experiments on running-amount prediction and urban perception across Tokyo, Milan, and Seattle demonstrate that Urban-MAS substantially reduces errors compared to single-LLM baselines. Ablation studies indicate that Predictive Factor Guidance Agents are most critical for enhancing predictive performance, positioning Urban-MAS as a scalable paradigm for human-centered urban AI prediction. Code is available on the project website:https://github.com/THETUREHOOHA/UrbanMAS

There is a prevailing trend to study urban morphology quantitatively thanks to the growing accessibility to various forms of spatial big data, increasing computing power, and use cases benefiting from such information. The methods developed up to now measure urban morphology with numerical indices describing density, proportion, and mixture, but they do not directly represent morphological features from the human's visual and intuitive perspective. We take the first step to bridge the gap by proposing a deep learning-based technique to automatically classify road networks into four classes on a visual basis. The method is implemented by generating an image of the street network (Colored Road Hierarchy Diagram), which we introduce in this paper, and classifying it using a deep convolutional neural network (ResNet-34). The model achieves an overall classification accuracy of 0.875. Nine cities around the world are selected as the study areas with their road networks acquired from OpenStreetMap. Latent subgroups among the cities are uncovered through clustering on the percentage of each road network category. In the subsequent part of the paper, we focus on the usability of such classification: we apply our method in a case study of urban vitality prediction. An advanced tree-based regression model (LightGBM) is for the first time designated to establish the relationship between morphological indices and vitality indicators. The effect of road network classification is found to be small but positively associated with urban vitality. This work expands the toolkit of quantitative urban morphology study with new techniques, supporting further studies in the future.

To understand our global progress for sustainable development and disaster risk reduction in many developing economies, two recent major initiatives - the Uniform African Exposure Dataset of the Global Earthquake Model (GEM) Foundation and the Modelling Exposure through Earth Observation Routines (METEOR) Project - implemented classical spatial disaggregation techniques to generate large-scale mapping of urban morphology using the information from various satellite imagery and its derivatives, geospatial datasets of the built environment, and subnational census statistics. However, the local discrepancy with well-validated census statistics and the propagated model uncertainties remain a challenge in such coarse-to-fine-grained mapping problems, specifically constrained by weak and conditional label supervision. Therefore, we present Deep Conditional Census-Constrained Clustering (DeepC4), a novel deep learning-based spatial disaggregation approach that incorporates local census statistics as cluster-level constraints while considering multiple conditional label relationships in a joint multitask learning of the patterns of satellite imagery. To demonstrate, compared to GEM and METEOR, we enhanced the quality of Rwandan maps of urban morphology, specifically building exposure and physical vulnerability, at the third-level administrative unit from the 2022 census. As the world approaches the conclusion of many global frameworks in 2030, our work offers a new deep learning-based mapping technique that explicitly encodes well-validated census and experts' belief systems to achieve an explainable and interpretable auditing of existing coarse-grained derived information at large scales.

Generative AI technologies are growing in power, utility, and use. As generative technologies are being incorporated into mainstream applications, there is a need for guidance on how to design those applications to foster productive and safe use. Based on recent research on human-AI co-creation within the HCI and AI communities, we present a set of seven principles for the design of generative AI applications. These principles are grounded in an environment of generative variability. Six principles are focused on designing for characteristics of generative AI: multiple outcomes & imperfection; exploration & control; and mental models & explanations. In addition, we urge designers to design against potential harms that may be caused by a generative model's hazardous output, misuse, or potential for human displacement. We anticipate these principles to usefully inform design decisions made in the creation of novel human-AI applications, and we invite the community to apply, revise, and extend these principles to their own work.

The network metaphor in the analysis of urban and territorial cases has a long tradition especially in transportation/land-use planning and economic geography. More recently, urban design has brought its contribution by means of the "space syntax" methodology. All these approaches, though under different terms like accessibility, proximity, integration,connectivity, cost or effort, focus on the idea that some places (or streets) are more important than others because they are more central. The study of centrality in complex systems,however, originated in other scientific areas, namely in structural sociology, well before its use in urban studies; moreover, as a structural property of the system, centrality has never been extensively investigated metrically in geographic networks as it has been topologically in a wide range of other relational networks like social, biological or technological. After two previous works on some structural properties of the dual and primal graph representations of urban street networks (Porta et al. cond-mat/0411241; Crucitti et al. physics/0504163), in this paper we provide an in-depth investigation of centrality in the primal approach as compared to the dual one, with a special focus on potentials for urban design.

The growing demand for detailed building roof data has driven the development of automated extraction methods to overcome the inefficiencies of traditional approaches, particularly in handling complex variations in building geometries. Re:PolyWorld, which integrates point detection with graph neural networks, presents a promising solution for reconstructing high-detail building roof vector data. This study enhances Re:PolyWorld's performance on complex urban residential structures by incorporating attention-based backbones and additional area segmentation loss. Despite dataset limitations, our experiments demonstrated improvements in point position accuracy (1.33 pixels) and line distance accuracy (14.39 pixels), along with a notable increase in the reconstruction score to 91.99%. These findings highlight the potential of advanced neural network architectures in addressing the challenges of complex urban residential geometries.

Urban systems are composed by complex couplings of several components, and more particularly between the built environment and transportation networks. Their interaction is involved in the emergence of the urban form. We propose in this chapter to introduce an approach to urban morphology grasping both aspects and their interaction. We first define complementary measures, study their empirical values and their spatial correlations on European territorial systems. The behavior of indicators and correlations suggest underlying non-stationary and multi-scalar processes. We then introduce a generative model of urban growth at a mesoscopic scale. Given a fixed exogenous growth rate, population is distributed following a preferential attachment depending on a potential controlled by the local urban form (density, distance to network) and network measures (centralities and generalized accessibilities), and then diffused in space to capture urban sprawl. Network growth is included through a multi-modeling paradigm: implemented heuristics include biological network generation and gravity potential breakdown. The model is calibrated both at the first (measures) and second (correlations) order, the later capturing indirectly relations between networks and territories.

Layout Generation aims to synthesize plausible arrangements from given elements. Currently, the predominant methods in layout generation are Generative Adversarial Networks (GANs) and diffusion models, each presenting its own set of challenges. GANs typically struggle with handling discrete data due to their requirement for differentiable generated samples and have historically circumvented the direct generation of discrete labels by treating them as fixed conditions. Conversely, diffusion-based models, despite achieving state-of-the-art performance across several metrics, require extensive sampling steps which lead to significant time costs. To address these limitations, we propose \textbf{DogLayout} (\textbf{D}en\textbf{o}ising Diffusion \textbf{G}AN \textbf{Layout} model), which integrates a diffusion process into GANs to enable the generation of discrete label data and significantly reduce diffusion's sampling time. Experiments demonstrate that DogLayout considerably reduces sampling costs by up to 175 times and cuts overlap from 16.43 to 9.59 compared to existing diffusion models, while also surpassing GAN based and other layout methods. Code is available at https://github.com/deadsmither5/DogLayout.

This chapter explores the concept of self-organization in urban planning and design, highlighting its role in shaping the unique characteristics of cities. It examines how various socio-economic, cultural, and political factors contribute to the development of distinct architectural styles, emphasizing the morphological patterns and self-organization principles. The chapter addresses the emergence of scaling laws and fractal geometry in urban forms, using historical and contemporary examples to illustrate these concepts. The discussion also delves into the cognitive aspects of urban design, examining how the physical layout of cities influences cognitive maps and perceptions of urban environments, and how these perceptions, in turn, influence urban design. Through the prism of self-organization, it demonstrates the dynamic interplay between individual and collective actions and the shaping of the urban landscape. This analysis offers insights into the complex, self-organizing systems that define urban spaces, emphasizing the interdependencies among architectural design, urban planning, and human cognition in shaping cityscapes.

Layout generation is a task to synthesize a harmonious layout with elements characterized by attributes such as category, position, and size. Human designers experiment with the placement and modification of elements to create aesthetic layouts, however, we observed that current discrete diffusion models (DDMs) struggle to correct inharmonious layouts after they have been generated. In this paper, we first provide novel insights into layout sticking phenomenon in DDMs and then propose a simple yet effective layout-assessment module Layout-Corrector, which works in conjunction with existing DDMs to address the layout sticking problem. We present a learning-based module capable of identifying inharmonious elements within layouts, considering overall layout harmony characterized by complex composition. During the generation process, Layout-Corrector evaluates the correctness of each token in the generated layout, reinitializing those with low scores to the ungenerated state. The DDM then uses the high-scored tokens as clues to regenerate the harmonized tokens. Layout-Corrector, tested on common benchmarks, consistently boosts layout-generation performance when in conjunction with various state-of-the-art DDMs. Furthermore, our extensive analysis demonstrates that the Layout-Corrector (1) successfully identifies erroneous tokens, (2) facilitates control over the fidelity-diversity trade-off, and (3) significantly mitigates the performance drop associated with fast sampling.

Controllable layout generation aims at synthesizing plausible arrangement of element bounding boxes with optional constraints, such as type or position of a specific element. In this work, we try to solve a broad range of layout generation tasks in a single model that is based on discrete state-space diffusion models. Our model, named LayoutDM, naturally handles the structured layout data in the discrete representation and learns to progressively infer a noiseless layout from the initial input, where we model the layout corruption process by modality-wise discrete diffusion. For conditional generation, we propose to inject layout constraints in the form of masking or logit adjustment during inference. We show in the experiments that our LayoutDM successfully generates high-quality layouts and outperforms both task-specific and task-agnostic baselines on several layout tasks.

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust layout control without the need for training or fine-tuning of the image generator. Our technique manipulates the cross-attention layers that the model uses to interface textual and visual information and steers the generation in the desired direction given, e.g., a user-specified layout. To determine how to best guide attention, we study the role of attention maps and explore two alternative strategies, forward and backward guidance. We thoroughly evaluate our approach on three benchmarks and provide several qualitative examples and a comparative analysis of the two strategies that demonstrate the superiority of backward guidance compared to forward guidance, as well as prior work. We further demonstrate the versatility of layout guidance by extending it to applications such as editing the layout and context of real images.

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each diffusion timestep, there is a different noise-to-data ratio and the timestep-dependent discriminator learns to distinguish the diffused real data from the diffused generated data. The generator learns from the discriminator's feedback by backpropagating through the forward diffusion chain, whose length is adaptively adjusted to balance the noise and data levels. We theoretically show that the discriminator's timestep-dependent strategy gives consistent and helpful guidance to the generator, enabling it to match the true data distribution. We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.

Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various techniques have been proposed to mitigate unwanted influences in diffusion models while preserving overall performance, achieving a balance between these goals remains challenging. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten. Our approach formulates this task as a constrained optimization problem using the value function, resulting in a natural first-order algorithm for solving the optimization problem. By altering the generative process to deviate away from the ground-truth denoising trajectory, we update parameters for preservation while controlling constraint reduction to ensure effective erasure, striking an optimal trade-off. Extensive experiments and thorough comparisons with state-of-the-art algorithms demonstrate that EraseDiff effectively preserves the model's utility, efficacy, and efficiency.

Sustainable urban design or planning is not a LEGO-like assembly of prefabricated elements, but an embryo-like growth with persistent differentiation and adaptation towards a coherent whole. The coherent whole has a striking character - called living structure - that consists of far more small substructures than large ones. To detect the living structure, natural streets or axial lines have been previously adopted to be topologically represent an urban environment as a coherent whole. This paper develops a new approach to detecting the underlying living structure of urban environments. The approach takes an urban environment as a whole and recursively decomposes it into meaningful subwholes at different levels of hierarchy or scale ranging from the largest to the smallest. We compared the new approach to natural street and axial line approaches and demonstrated, through four case studies, that the new approach is better and more powerful. Based on the study, we further discuss how the new approach can be used not only for understanding, but also for effectively designing or planning the living structure of an urban environment to be more living or more livable. Keywords: Urban design or planning, structural beauty, space syntax, natural streets, life, wholeness

Urban design profoundly impacts public spaces and community engagement. Traditional top-down methods often overlook public input, creating a gap in design aspirations and reality. Recent advancements in digital tools, like City Information Modelling and augmented reality, have enabled a more participatory process involving more stakeholders in urban design. Further, deep learning and latent diffusion models have lowered barriers for design generation, providing even more opportunities for participatory urban design. Combining state-of-the-art latent diffusion models with interactive semantic segmentation, we propose RECITYGEN, a novel tool that allows users to interactively create variational street view images of urban environments using text prompts. In a pilot project in Beijing, users employed RECITYGEN to suggest improvements for an ongoing Urban Regeneration project. Despite some limitations, RECITYGEN has shown significant potential in aligning with public preferences, indicating a shift towards more dynamic and inclusive urban planning methods. The source code for the project can be found at RECITYGEN GitHub.

Graph generation has been dominated by autoregressive models due to their simplicity and effectiveness, despite their sensitivity to ordering. Yet diffusion models have garnered increasing attention, as they offer comparable performance while being permutation-invariant. Current graph diffusion models generate graphs in a one-shot fashion, but they require extra features and thousands of denoising steps to achieve optimal performance. We introduce PARD, a Permutation-invariant Auto Regressive Diffusion model that integrates diffusion models with autoregressive methods. PARD harnesses the effectiveness and efficiency of the autoregressive model while maintaining permutation invariance without ordering sensitivity. Specifically, we show that contrary to sets, elements in a graph are not entirely unordered and there is a unique partial order for nodes and edges. With this partial order, PARD generates a graph in a block-by-block, autoregressive fashion, where each block's probability is conditionally modeled by a shared diffusion model with an equivariant network. To ensure efficiency while being expressive, we further propose a higher-order graph transformer, which integrates transformer with PPGN. Like GPT, we extend the higher-order graph transformer to support parallel training of all blocks. Without any extra features, PARD achieves state-of-the-art performance on molecular and non-molecular datasets, and scales to large datasets like MOSES containing 1.9M molecules. Pard is open-sourced at https://github.com/LingxiaoShawn/Pard.

This is an extended abstract for a presentation at The 17th International Conference on CUPUM - Computational Urban Planning and Urban Management in June 2021. This study presents an interdisciplinary synthesis of the state-of-the-art approaches in computer vision technologies to extract built environment features that could improve the robustness of empirical research in planning. We discussed the findings from the review of studies in both planning and computer science.

Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Planning (OUIP), which generates personalized urban itineraries from user requests in natural language. We then present ITINERA, an OUIP system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs. This involves decomposing user requests, selecting candidate points of interest (POIs), ordering the POIs based on cluster-aware spatial optimization, and generating the itinerary. Experiments on real-world datasets and the performance of the deployed system demonstrate our system's capacity to deliver personalized and spatially coherent itineraries compared to current solutions. Source codes of ITINERA are available at https://github.com/YihongT/ITINERA.

Artificial Intelligence (AI) is increasingly recognised for its ability to accelerate physics-based simulation tasks, making it particularly promising in urban design processes, where simulation often hinders iterative development. This review explores the intersection of AI, parametric urban design (PUD), and outdoor thermal comfort (OTC), assessed using the Universal Thermal Climate Index (UTCI) or other indices. We identify emerging methods and tools used to optimise comfort outcomes through intelligent design frameworks. By systematically analysing 40 studies from 2018 to 2025 and leveraging bibliometric analysis, the review categorises contributions into predictive modelling, generative design, parametric optimisation, and integration strategies. The limitation is the niche and novel nature of the subject, which reduces the number of eligible studies. We highlight how AI, particularly machine learning, acts as both a surrogate for environmental simulation and a driver for design generation. Although full integration of AI with parametric and comfort modelling remains limited, recent progress suggests strong potential. This paper presents a conceptual pipeline for integrating AI into PUD to support comfort optimisation, emphasising the need for open datasets, interpretable models, and design tool interoperability.  This review establishes the first interdisciplinary synthesis of parametric urban design, artificial intelligence, and outdoor thermal comfort research, providing urban planners with a framework to leverage emerging technologies for climate-resilient cities. Limitations include the niche nature of AI-PUD-OTC integration (41 studies met criteria) and the lack of longitudinal validation in built projects.

: [Objective] As urban design faces increasing demands for contextual responsiveness, iterative optimization

No abstract available

No abstract available

This paper delves into the role of artificial intelligence (AI) in urban design, focusing on its capability to manage complex urban systems via paradigm classification and comparative analysis. It methodically explores how AI improves design generation, optimizes morphology, and simulates real-world scenarios, thereby enhancing design quality and efficiency throughout the urban design process. Furthermore, the study contributes to the development of comprehensive AI evaluation criteria, integrating both theoretical and practical perspectives to critically understand the advantages and limitations of AI in urban design applications.

Rapid urbanization, alongside escalating resource depletion and ecological degradation, underscores the critical need for innovative urban development solutions. In response, sustainable smart cities are increasingly turning to cutting-edge technologies—such as Generative Artificial Intelligence (GenAI), Foundation Models (FMs), and Urban Digital Twin (UDT) frameworks—to transform urban planning and design practices. These transformative tools provide advanced capabilities to analyze complex urban systems, optimize resource management, and enable evidence-based decision-making. Despite recent progress, research on integrating GenAI and FMs into UDT frameworks remains scant, leaving gaps in our ability to capture complex urban flows and multimodal dynamics essential to achieving environmental sustainability goals. Moreover, the lack of a robust theoretical foundation and real-world operationalization of these tools hampers comprehensive modeling and practical adoption. This study introduces a pioneering Large Flow Model (LFM), grounded in a robust foundational framework and designed with GenAI capabilities. It is specifically tailored for integration into UDT systems to enhance predictive analytics, adaptive learning, and complex data management functionalities. To validate its applicability and relevance, the Blue City Project in Lausanne City is examined as a case study, showcasing the ability of the LFM to effectively model and analyze urban flows—namely mobility, goods, energy, waste, materials, and biodiversity—critical to advancing environmental sustainability. This study highlights how the LFM addresses the spatial challenges inherent in current UDT frameworks. The LFM demonstrates its novelty in comprehensive urban modeling and analysis by completing impartial city data, estimating flow data in new locations, predicting the evolution of flow data, and offering a holistic understanding of urban dynamics and their interconnections. The model enhances decision-making processes, supports evidence-based planning and design, fosters integrated development strategies, and enables the development of more efficient, resilient, and sustainable urban environments. This research advances both the theoretical and practical dimensions of AI-driven, environmentally sustainable urban development by operationalizing GenAI and FMs within UDT frameworks. It provides sophisticated tools and valuable insights for urban planners, designers, policymakers, and researchers to address the complexities of modern cities and accelerate the transition towards sustainable urban futures.

The rapid evolution of Artificial Intelligence (AI) brings new opportunities and challenges in various sectors, including urban design. Indonesia is currently undergoing massive development, marked by the relocation of the capital to IKN Nusantara, which envisions the capital as a smart city that demands complexity in its realization. So, exploring AI technology in the design process becomes an opportunity. This research explores urban planning and design methods by employing AI technology collaboratively with human thinking in the West IKN Area. This research method involves using 3 AI, from ChatGPT 3.5 and Bard AI for planning brainstorming process, Autodesk Forma for 3D design simulation, and ReRender AI for realistic scene visualization, where these 3 processes also collaborate with human ability. So, the findings of this research highlight the role and involvement of AI and humans in every urban design process, where AI can make a valuable contribution. However, the final decision and creativity still come from human thinking. It is hoped that this exploratory study of urban design involving AI can provide new insights for urban actors regarding new dimensions in the planning and design process that continuously evolve with technology.

The rise of Artificial Intelligence (AI) has raised concerns about its potential to dominate various fields globally. Society 5.0 emerged as a response to these concerns and the anticipation of the Industrial Revolution 4.0. However, AI has also created new issues, particularly in urban design, by displacing the work of creative designers. The concept of Society 5.0 aims to address these concerns and promote global progress. This research aims to demonstrate how AI might be used in the urban design process, as well as how HNI could balance the technological developments that are occurring. This research uses an exploratory qualitative method by exploring AI as a supporting tool in the planning and design process, such as data collection and initial conception. The concept is then developed into an organized and systematic design as well as the 3D models. The AI tools used in this research are ChatGPT, Chatmind, Leonardo AI, and Autodesk Forma. The result of this research has revealed how AI, as part of digital transformation, could play its role in designing a sustainable area. Nevertheless, human intervention would still be necessary to comprehend a design’s context.

This study, based on multi-source data fusion and artificial intelligence analysis methods, systematically investigated the optimization of green infrastructure in the old urban districts of Huangpu District, Shanghai. By integrating six major types of data sources including Sentinel-2 remote sensing images, Baidu Street View images, mobile phone signaling data, and environmental monitoring data, a comprehensive evaluation system covering three dimensions: spatial distribution, quality and efficiency, and health benefits has been constructed. The research adopts a deep learning model to calculate the green view rate, uses the random forest algorithm to analyze the thermal environment effect, and establishes a supply and demand matching index to identify hotspots. The results show that the green space coverage rate in the study area is only 12.3%, and 38.7% of the residents live outside the 500-meter service radius of the park. The green vision rate varies significantly in space (over 25% for main roads and less than 8% for alleys and lanes). Three renovation schemes are proposed through the multi-objective optimization model. It is expected that the service population can be increased by 28,000 people, the green vision rate can be raised to 18.5%, and the regional temperature can be reduced by 0.9℃. This study provides a data-driven decision support method for the optimization of green infrastructure in high-density old urban areas.

This paper presents a comparative study on the transdisciplinary design of resilient urban subcenters, examining the interplay between human-led and artificial intelligence (AI)-generated design approaches. By employing holistic design methods, we prepare and present revitalization projects for two areas of urban space. Our goal was to create a resilient urban subcenter that contributes to the development of a resident. The first revitalized site reflects the multicultural past of the city. The second project addresses the need to revitalize a subcenter reserved for residents. In the non-AI approach, holistic design is implemented across various universities, fields, and academic disciplines—the humanities, social sciences, engineering, and the arts. Transdisciplinary teams of sociologists, engineers, interior designers, architects, urban geographers, and acousticians transcend workshop limitations as well as cognitive boundaries, promoting the creation of new, unconventional knowledge. The AI-integrated approach employs artificial intelligence in a dual capacity: both as a generator of alternative design visions and as an analytical tool for assessing technological readiness. The findings contribute to the evolving discourse on sustainable urban development and the transformative potential of technology in transdisciplinary design practices.

This research focuses on the generation of urban public space color design schemes using Artificial Intelligence (AI). The designed AI-based system predicts colors for the environment, culture, and users and designs a color palette for smart cities. Neural networks and clustering algorithms are used to determine the best hues and shades, depending on the input parameters like climate, architectural style, and general looks in a specific region. It evokes sophisticated colors in varied urban contexts, URBAN FABRICS proposes a specific color answer to the aesthetic and performative beautification of the public realm. In addition to adopting elements of AI binding into the design principles, the system enables dynamic colors to adapt to the changing needs and external conditions. Testing the model in multiple cities demonstrated its ability to generate unique, context-sensitive designs, improving both aesthetic value and user satisfaction. This research highlights the role of AI in modern urban planning, presenting an innovative approach to color design that balances artistic creativity with data-driven insights. The findings offer practical implications for architects, urban planners, and designers seeking to enhance urban public spaces through personalized, AI-assisted color schemes.

Intelligent transformation of urban landscape design has become a key direction to improve design efficiency and quality. Based on deep learning technology, an urban landscape design assisted decision-making system is constructed, which innovatively puts forward the landscape element identification algorithm and multi-dimensional evaluation model, and designs the scheme recommendation algorithm based on deep reinforcement learning and decision-making algorithm of multi-objective optimisation. Through the system practice verification, the method significantly improves the intelligent level of landscape design and decision-making scientificity, and provides a new technical path for the construction of smart city.

No abstract available

ABSTRACT New digital technologies and systems are being extensively applied in urban contexts. These technologies and systems include algorithms, robotics, drones, Autonomous Vehicles (AVs) and autonomous systems that can collectively be labelled as Artificial Intelligence (AI). Critical debates have recognized that these various forms of AI do not merely layer onto existing urban infrastructures, forms of management and practices of everyday life. Instead, they have social and material power: they perform work, anticipate and assess risks and opportunities, are aberrant or glitchy, cause accidents, and make new demands on humans as well as the design of cities. And yet, urban scholars have only recently started to engage with research on urban AI and to begin articulating research directions for urban development beyond the current focus on smart cities. To enhance this engagement, this intervention explores three sets of questions: what is distinctive about this novel way of thinking about and doing cities; what are the emerging mutual interdependencies and interrelations between AI and their urban contexts; and what are the consequent challenges and opportunities for urban governance. In closing, we outline research directions shaped around new research questions raised by the emergence of urban AI.

Limited accessibility and safety for women and persons with disabilities remain critical issues in urban development in Indonesia, particularly in public spaces that are insufficiently responsive to vulnerable groups. This study aims to develop an inclusive urban design concept based on gender and disability perspectives through the integration of Artificial Intelligence (AI) and participatory approaches as an evidence-based design foundation. The research adopts a Design-Based Research (DBR) approach using mixed methods that combine AI-based quantitative analysis and participatory qualitative methods. Quantitative data were obtained through YouTube data crawling (853 entries, 729 valid datasets) and analyzed using Named Entity Recognition (NER) to identify potentially unsafe urban locations, then visualized through WebGIS. Qualitative data were collected through Focus Group Discussions (FGDs) involving disability organizations, women’s groups, and policymakers. The results identified three vulnerable locations in Surabaya: Kedung Cowek Street, Wonorejo Timur Street, and Kupang Indah Street. The study formulates inclusive urban design elements, including standardized pedestrian pathways, guiding blocks, gentle ramps, lighting levels of at least 12 lux, accessible transit stops, signage, and gender-sensitive public facilities. The novelty lies in integrating AI-based social media analysis with participatory approaches within a DBR framework to support data-driven inclusive urban design.

No abstract available

China’s hyper-growth cities face unprecedented uncertainty arising from intertwined economic, social, and environmental stresses that challenge traditional static approaches to urban planning. This article introduces the novel concept of adaptive urban morphogenesis—an evolving and dynamic configuration of urban structure and function—enabled by the synergistic integration of quantum computing (QC) and artificial intelligence (AI). We propose employing QC to manage inherent uncertainties and to deliver computationally feasible multi-objective combinatorial optimization solutions, such as dynamic resource allocation and resilient infrastructure design. In parallel, AI processes extensive urban datasets, extracts complex patterns, and generates real-time predictive insights. Together, these technologies establish a closed-loop feedback system: AI feeds QC simulations with predictions, while QC delivers the best adaptive solutions under uncertainty that subsequently inform AI models. This framework is designed to capture the rapid evolution of China’s urban economies and offers a paradigm shift toward forward-thinking, simulation-driven urban planning.

The burgeoning resurgence of interest in artificial intelligence (AI) is transforming urban planning and design. While studies have leveraged AI for generative planning and design, the focus has been on augmenting the capabilities of planners and designers, often overlooking public participation. Addressing this gap, this study proposes a new AI-aided and data-driven (AIDD) framework that integrates design, science, and participation to support participatory generative planning and design. Demonstrated in a hypothetical design case, this framework allows users with limited expertise to generate designs that resemble favored urban forms, meet zoning requirements, and improve safety perception performance.

In an urban context, the use of artificial intelligence (AI) can help to categorise and analyse large amounts of data quickly and efficiently. The AI approach can make municipal administration and planning processes more efficient, improve environmental and living conditions (e.g., air quality, inventory of road damages, etc.), or strengthen the participation of residents in decision-making processes. The key to this is “machine learning” that has the ability to recognise patterns, capture models, and learn on the basis of big data via the application of automated statistical methods. However, what does this mean for urban planning and the future development of cities? Will AI take over the planning and design of our cities and actively intervene in and influence planning activities? This article applies a systematic literature review supplemented by case study analyses and expert interviews to categorise various types of AI and relate their potential applications to the different phases of the planning process. The findings emphasize that AI systems are highly specialised applications for solving and processing specific challenges and tasks within a planning process. This can improve planning processes and results, but ultimately AI only suggests alternatives and possible solutions. Thus, AI has to be regarded as a planning tool rather than the planning solution. Ultimately, it is the planners who have to make decisions about the future development of cities, taking into account the possibilities and limitations of the AI applications that have been used in the planning process.

This study proposes a scenario-based conceptual model for transforming underground parking structures into sustainable interior green spaces, directly addressing two core research dimensions: energy efficiency and user experience. The originality of the research lies in repositioning subterranean spaces—often overlooked in urban planning—as climate-responsive, multi-functional public environments. Using a site-specific case in downtown Rize, Türkiye, three design scenarios—passive green walls, active modular systems, and experimental micro-farming—were comparatively analyzed. These scenarios were assessed through AI-assisted simulations and climate-based performance evaluations in terms of environmental benefits, thermal regulation, carbon reduction, and experiential quality. Underground space leads to green design interventions, which in turn generate environmental, energy, and social benefits. The results demonstrate that passive systems provide cost-effective improvements, active modular systems achieve balanced performance, and experimental micro-farming yields the highest ecological and social benefits. The study uniquely contributes to urban sustainable design by integrating climate-adaptive strategies, biophilic design principles, and AI-supported visualization into the transformation of underground structures. This research not only advances academic discourse but also provides policy-relevant insights for local governments, developers, and communities in the context of urban renewal.

Urban and regional planning faces unprecedented challenges in the 21st century, ranging from rapid urbanization and population growth to climate change and resource depletion. In addressing these challenges, artificial intelligence (AI) has emerged as a transformative toolset for planners, offering advanced analytics, predictive modeling, and optimization capabilities. In this paper, the author discusses how artificial intelligence can be integrated into urban and regional planning in India’s socio-economic landscape. It highlights the use of machine learning to predict future trends and interpret complex data sets, geospatial analysis using various AI-powered tools for spatial planning, as well as Natural Language Processing for data mining. As a way of understanding and improving urban infrastructure, deep learning techniques can be used in urban image analysis and agent-based modeling along with urban simulation for better prediction and decision-making. Nevertheless, a great number of actors make it difficult to implement such techniques locally such as the absence of valuable local data, limited infrastructure facilities, professional knowledge gaps among employees and their poor integration into existing planning processes. The article strongly stresses institutional capacity building, interagency cooperation through governance structures and open data initiatives. Importantly, there has been an indication that the Indian government is committed to artificial intelligence based on various initiatives and policies showing its willingness to embrace these technologies despite their minimal direct application in Indian urban and regional development so far

Introduction: Challenges for sustainable urban development are especially related to resource demand, levels of pollution, and infrastructure planning for urbanization. Faced with rapid urban growth we must adopt new approaches to ensure most of the human race continues to live in cities yet these remain liveable and resilient. Predictive analytics using AI has the potential to improve urban planning by using it to manage resources and increase environmental sustainability.Methodology: To study the effect of AI on urban growth and sustainability, a randomized block design was applied. Machine learning (ML) models trained with data from municipal sources, remote sensing platforms, and socioeconomic surveys using neural networks, decision trees, and support vector machines are constructed. Predicted values of the key urban parameters were obtained and the accuracy of the model was measured by MAE, RMSE, and cross-validation.Results: The models of AI showed that Metropolis City would see a 15 percent increase in energy demand and a 12 percent increase in water consumption. AI predicts also areas where to increase green spaces and make more efficient public transport. AI solutions proposed ways towards better environmental and resource management despite higher pollution levels and waste generation.Conclusion: Predictive models designed by AI offer a great deal of information on how cities can go green and manage growth as well as resources use. Inspired, particularly through neural networks, these models show high potential for infrastructure optimization in the city, environmental sustainability improvement, and realizing resource management.

Abstract This study accurately assessed the overall ecological landscape condition of the city through the environmental landscape pattern index, and specifically explored the NP, LSI, and PD indices of construction land, cultivated land, forest land, grassland, water, and other land. Adopting advanced artificial intelligence and virtual reality technologies, this paper successfully constructs a 3D visualization scene of the urban landscape, which provides a vivid and intuitive perspective for urban planning. Further, based on the planning and design framework of urban landscape ecosystem, this paper clarifies the ecological evaluation elements and landscape design indexes, and uses VR technology to optimize the design of environmental aspects of urban streets. By establishing an optimization strategy database, this paper conducts an in-depth correlation analysis between the optimization scheme’s design indicators and evaluation factors. Comparing the comprehensive ecosystem service area before and after optimization, the results show that applying VR technology in ecological landscape design is highly effective. The integrated ecosystem service area before and after optimization increased from 7611.72m² to 8039.51m², of which the integrated ecosystem service area of “general” grade increased by 324.03m², showing the best effect of ecological optimization. The research in this paper provides scientific basis and technical support for ecological landscape design and new ideas and methods for future urban environmental planning and construction.

This paper elucidates an approach that utilizes generative AI to develop alternative architectural design options based on local identity. The advancement of AI technologies has increasingly piqued the interest of the AEC-FM (architecture, engineering, construction and facility management) industry. Notably, the topic of ‘visualization’ has gained prominence as a means for enhancing communication related to a project, especially in the early phases of design. This study aims to enhance the ease of obtaining design images during initial phases of design by drawing from multiple texts and images. It develops an additional training model to generate various design alternatives that resonate with the identity of the locale through the application of generative AI to the façade design of buildings. The identity of a locality in cities and regions is the capacity for the cities and regions to be identified and recognized as a specific area. Among the various visual elements of urban and regional landscapes, the front face of buildings may play a significant role in people's aesthetic perception and overall impression of the local environment. The research proposes an approach that transcends the conventional employment of three-dimensional modeling and rendering tools by readily deriving design alternatives that consider this local identity in commercial building remodeling. This approach allows for financial and temporal efficiency in the design communication phase of the initial architectural design process. The implementation and utilization of the proposed approach's supplementary training model in this study proceeds as follows: 1) image data are collected from the target area using open-source street-view resources and preprocessed for conversion to a trainable format; 2) textual data are prepared for pairing with preprocessed image data; 3) additional training and outcome testing are performed using varied text prompts and images; 4) the ability to generate building façade images that reflect the identity of the collected locale by using the additional trained model is determined, as evidenced by the findings of the proposed application method study. This enables the generation of design alternatives that integrate regional styles and diverse design requirements for buildings. The training model implemented in this study can be leveraged through weight adjustments and prompt engineering to generate a greater number of design reference images, among other diverse approaches.

Abstract In recent years, the rapid development of artificial intelligence (AI) technology has brought new opportunities to the field of education. With its powerful data processing and analysis capabilities, AI technology has shown great potential in the integration of educational resources and personalized teaching. Specifically in the realm of design education, AI technology holds immense potential to enhance our comprehension of the cultural essence of urban public spaces, elevate the standards of design education, and thereby foster a generation of design talents equipped with both innovative thinking and practical proficiency. The objective of this study is to delve into the application and impact of AI technology in the educational setting, against the backdrop of cultural preservation and urban public space innovation. By conducting a comparative analysis between an experimental group and a control group, this research aims to thoroughly examine the role AI technology plays in augmenting students’ spatial design proficiency, cultural comprehension, and innovative thinking capabilities. The research results show that AI technology significantly improves students’ abilities in the above three aspects by providing personalized learning paths, rich learning resources, and real-time learning feedback. Specifically, students’ spatial design abilities such as spatial composition and color matching have been improved, their ability to understand and appreciate different cultures has also been enhanced, and their innovative thinking and imagination have also been effectively stimulated. This study provides the theoretical basis and practical guidance for educators to better integrate AI technology into teaching, which helps promote the inheritance and innovation of urban public space culture.

No abstract available

The application of AI technology in urban planning covers multiple levels, such as data analysis, decision support, and automated planning. Urban research relies on AI technology to understand and summarize the law of urban growth and improve the analysis of the evolution trend of urban space. Planning and design use AI technology to explore the relevant factors affecting urban development and their weights and discuss the critical role of green building technology in the sustainable development of the construction industry. With the increase in global energy consumption and carbon emissions, traditional building methods can no longer meet environmental protection requirements and efficient use of resources. As a sustainable development solution, green building technology has been paid more and more attention to and adopted by people. These technologies focus not only on the energy efficiency and environmental impact of buildings but also on the resource utilization and environmental load of green buildings over their entire life cycle driven by machine learning. This paper details the basic principles and applications of green building technologies, including AI-driven reduction of negative environmental impacts, improvement of occupant health, efficient use of resources, and optimization of indoor environmental quality. This paper focuses on the critical role of the LEED assessment system developed by the U.S. Green Building Council in advancing green building practices. In addition, the paper analyzes vital points such as water use in green building design, machine learning-driven wind environment optimization, solar technology application, and practical application cases of these technologies on a global scale.

The possibilities of using artificial intelligence (AI) in architectural and urban planning activities are considered. The authors analyze the possibilities of using AI in the design, planning and management of the urban environment. The role of machine learning and data analytics in creating new and sustainable architectural solutions is also highlighted. The advantages and challenges of using AI in this area are highlighted. Recommendations are proposed for the further development and integration of AI technologies into architectural design and urban planning using the example of digital twin technology.