In compact cities, one of the main challenges is the competition for limited urban land resources between people and vehicles, where shared parking infrastructure may offer a potential solution. Building on existing literature, this study presents a technical framework for the time-division multiplexing strategy of transportation infrastructure, and explores its application in an old central urban area in China as a case study. This strategy includes three main steps: supply and demand identification, planning and design, and community promotion. Firstly, from macro to micro scales, identify characteristics of parking lots' usage rates and the public activity demands based on mobile signaling data and field survey results. Secondly, develop the time-division multiplexing rules for parking lots according to the above characteristics and detailed spatial planning and design schemes. Finally, design an interactive model that can provide the public's real-time feedback to ensure effective implementation of the schemes by guiding public behavior. Grounded in compact city theories, this approach extends spatial land use limitations by introducing a temporal dimension. By blending big data coverage with field surveys and interviews, and integrating planning and design with public participation, this study offers an effective solution to urban conflicts between people and vehicles.

● Focuses on time-division multiplexing strategies to address people and vehicle conflict by optimizing the use of limited space over time

As a highly urbanized bay area bustling with socio-economic activities, Shenzhen Bay is a pivotal stopover and wintering habitat for migratory birds along the East Asian-Australasian Flyway. The Futian Mangrove National Important Wetland, located in the northeast of Shenzhen bay, is a part of the Guangdong Neilingding–Futian National Nature Reserve. As the smallest national nature reserve in China, the wintering habitat of migratory birds has been significantly impacted by the compacted surrounding built-up environment. It has become an urgent need for refined high-quality ecological restoration for the habitats. This project leveraged Nature-based Solutions to develop a refined model for the ecological restoration of coastal wetland waterbird habitats in compact urban areas. By analyzing waterbird behaviors and habitat requirements, this model outlined six strategies: water surface expansion, water level control, hydrodynamic conditions improvement, shoal transformation, adaptive vegetation management, and disturbance control. To effectively guide the restoration implementation, high-, medium-, and low-adaptive approaches were proposed accordingly. After restoration in 2022, notable increases in target species, such as Platalea minor, were observed. The variety of waterbirds of the reserve in 2022 increased by 33% compared with 2021, while increased by 50.9% compared with 2016, significantly enhancing ecosystem services of the coastal area. As urban renewal in China is shifting towards spatial redevelopment, this model offers valuable insights for ecological restoration aiming at coastal wetland waterbird conservation across the country, and substantially supports establishing the "International Mangrove Center" in Shenzhen.

● Explores Nature-based Solutions on refined coastal wetland restoration in highly urbanized area

This study introduces a Landscape Information Modeling–Stable Diffusion (LIM–SD)-based digital workflow for ecological engineered landscaping (EEL) design, focusing on urban river wetlands. It explores how students from diverse academic backgrounds perform EEL tasks using the LIM–SD approach. A total of 30 participants, including industrial design postgraduates and landscape architecture undergraduates and postgraduates, completed the design tasks. The efficacy of their designs was assessed through expert evaluations on site appropriateness, aesthetics, spatial layout, and eco-engineering techniques of the design proposals, as well as the parametric simulation which calculated the vegetation coverage rate and proportion of riparian areas for each design. Moreover, evaluation of participants' subjective design experiences was conducted via questionnaires. Results indicated that landscape architecture postgraduates outperformed others applying ecological engineering principles. The study also elucidated discrepancies between LIM models and SD-generated renderings, as well as the uncertainty of SD-generated renderings, suggesting improvements are needed to align digital outputs with ecological design criteria.

As global climate continues to change, it is pressing to integrate the carbon peaking and carbon neutrality goals into territorial spatial planning. While little existing ecological restoration research focuses on counties in western China, particularly arid areas of northwest China, this research took Wensu County of the Xinjiang Uygur Autonomous Region in China as the study case, evaluated the carbon sequestration capacity and carbon storage of the current carbon sinks, identified the spatial pattern of carbon sinks, and proposed the territorial ecological restoration approaches to increasing carbon sinks. The evaluation results show that the importance level of carbon sinks varies significantly across geographical environments of the county, where one primary carbon sink, two secondary carbon sinks, and potential carbon sinks with a total area of 2259.81 km² were identified. This research extracted eight typical land use patterns based on current land use and proposed ecological restoration strategies accordingly. This research shows a way to integrate carbon peaking and carbon neutrality goals in territorial spatial planning, which is instrumental for carbon sink management in the arid areas of northwest China and provides a referable paradigm for regions with similar geographical conditions.

● Focuses on ecological restoration in a county in the arid areas of northwest China, aiming for carbon sink increase

Facing the challenges of global climate change, the construction of low-carbon cities has become an inevitable pathway, where carbon emission assessment is a critical part to the transition towards digitalized urban planning and design of low-carbon cities. However, comprehensive review on carbon assessment tools applied to urban planning and design is absent. As a response, this paper selected and reviewed typical digital assessment tools of carbon emissions at both the city and district/neighborhood scales, and summarized their measuring dimensions and reference data. Currently, tools based on energy system planning and operational energy simulation dominate the field, while tools for carbon emission and carbon sink estimations based on land use types or materials are rapidly developing due to the increasing refinement of carbon emission assessments and shifts of decarbonization policies. At present, these tools are primarily used in energy planning and design, governmental decision-making, and building structural design and material choice, and their application in urban planning and design practice, especially in the early stages, remains limited. Hence, this study further underscored the limitations and potential development directions of existing carbon emission assessment tools by case studying low-carbon practices worldwide that have not utilized digital assessment tools—in the future, improving tools' flexibility and adaptability for diverse scenarios, building comprehensive databases, incorporating the calculation of operational carbon, embedded carbon, and carbon sinks, and aligning with the needs for multi-dimensional, multi-criteria, and full-process assessments should be put into more efforts.

● Summarizes five categories of carbon emission assessment tools at both city and district/neighborhood scales

Design increasingly plays a pivotal role in achieving justice for all. However, there are often gaps between visions and implementation due to the variety of factors and stakeholders involved in design practice. Through literature review and a keyword co-occurrence analysis, this paper investigates current landscape justice research and identifies the distinguishing concerns in design, and highlights the importance of systematic thinking in achieving landscape justice. By examining the practices of the British company Building Design Partnership (BDP), a multinational design company, this paper identifies BDP’s three key design principles as experiences can be followed for landscape justice: design for inclusion, design for resilience, and design for future ecosystems. The paper also addresses potential challenges and conflicts in implementing landscape justice across different contexts and highlights multinational design companies’ efforts to mediate between various stakeholders. Finally, this paper demonstrates that design companies can contribute to 1) bridging social and environmental justice through landscape design, 2) achieving the visions promoted by scholars, 3) identifying and deploying diverse approaches to achieving landscape justice with their sensitivity to practical problems, and 4) fostering integrated feedback loops via both top-down and bottom-up approaches to ensure effective implementation of landscape justice.

● Investigates current landscape justice research and identifies the gap between theories and design practice through a keyword co-occurrence analysis

Faced with the future decentralization trends of intelligent agent distribution in urban neighborhoods, this article proposes a new, integrated pathway of “intelligent construction + scenario operation.” Its innovativeness lies in incorporating intelligent technology into processes of urban design, neighborhood renewal, and scenario operation. The pathway is tested through the empirical research on the case of the Shanghai Vanke Future City (NEXUS) project. In this project, the “intelligent construction + scenario operation” pathway is mainly demonstrated in scenarios of “intelligent transportation,” “convenient living,” “inclusiveness and security,” and “environmental governance.” The project becomes the model of combining production, ecology, and living together under Shanghai’s new city strategy, and has gained positive social impacts. It verifies that the pathway is conducive to improving the design, construction, and operation qualities of future urban neighborhoods, providing a reference for China’s smart neighborhood construction in the future.

● Proposes a pathway of "intelligent construction + scenario operation" for smart neighborhoods of future city

Artificial intelligence (AI) image generation is revolutionizing traditional workflow in landscape architecture industry, among which the "image-to-image" generative adversarial network (GAN) exhibits potential to facilitate concept design. Therefore, it underscores the importance of applicability evaluation from the perspective of users. This research aims to evaluate the quality of the GAN-generated results, their effectiveness in integrating with design workflows, and the landscape architects' acceptance of the results through image analysis and user survey. The evaluation focuses on layout generation and masterplan rendering within the Pix2Pix–BicycleGAN workflow. The evaluation metrics of image analysis including block number absolute/Euclidean distance, histogram distance, and structural similarity index measure, were employed. Additionally, the online survey with two questionnaires was conducted to evaluate the visual realism and preference for color and texture of the GAN-generated results. The findings indicate that the GAN-generated layout exhibits a high similarity to the human-designed layout, and the GAN-rendered masterplans fulfill the criteria for concept design and garner positive user acceptance. Conclusively, this study delves into the intrinsic rationality of the GAN generation methods and limitations in professional ethics and data bias, reflecting on the gaps between current AI-assisted design methods and evidence-based design.

● Quantitative applicability evaluation of "image to image" landscape masterplan generation method

This paper explores the application of digital twins (DT) in urban planning and landscape design. Initially developed in fields such as manufacturing and engineering, DT has emerged as a critical tool for replicating and simulating the physical world within a virtual environment. Its application enables real-time monitoring and future transformation simulations, offering profound implications for urban planning and landscape design. Despite its broad applicability, implementing DT in less controlled contexts like urban landscape environments presents unique challenges, particularly drawing skepticism around the feasibility of launching a universal city-level DT. This paper advocates for site-scale DTs focusing on specific urban elements, such as parks, buildings, and infrastructure, to enable more controlled and effective modeling environments, emphasizing the importance of creating an urban DT network through serial site-scale DTs. This approach requires ongoing experimentation in landscape and urban design practices and supportive economic and policy environments to foster interdisciplinary research and design and market adoption. Drawing from three design proposals, this paper explores the transformative potential of site-scale DTs, highlighting its role in creating more interactive, participatory, and responsive environments by integrating citizen data on emotions, interactions, and health factors, thereby advancing the design-intervened virtual-physical interface of public spaces and urban landscapes.

● Advocates for site-scale DT to enhance integration with existing urban design and planning practices

The katsura tree at Dumbarton Oaks is among the oldest of the species in North America and pre-dates the design of the garden. Japanese master gardener Kurato Fujimoto was commissioned to inspect and lead the construction and installation of a series of branch supports, known as "hoozue" in Japan, to rejuvenate this venerable tree that was in decline. The assessment of the tree included the inspection of the branch structure with a projection toward post-installation growth over the next several decades. Materials such as rope, bark fabric, nails (kasugai), and the wooden hoozue themselves were fabricated and installed with indigenous knowledge and experience, which were described in the text and drawings and documented in a series of photographic sequences. This article narrates the process of this preservation work, demonstrating the significance of this indigenous Japanese technique.

● It studies an indigenous Japanese arboriculture technique that has time-tested success yet may be different from accepted practices

As social and economic dynamics continue to evolve and the demand for companionship increases, pet ownership has become an increasingly popular lifestyle choice. Pet parks, as a new form of urban public space, are gaining significant attention. This study, grounded in the theory of spatial justice, employs a combination of questionnaires and semi-structured interviews to evaluate four representative pet parks in Hong Kong, China. It explores how pet parks, as inclusive green infrastructure in high-density environments, contribute to urban community well-being and broader spatial justice. The study reveals the conflicts between pet owners and non-pet owners regarding the rights to use public spaces, examining how to guarantee the spatial rights of specific groups while avoiding harm to others. The findings indicate that green space availability, sociability and participation, walkability, safety, and flexibility in pet parks play a positive role in achieving urban spatial justice. However, pet parks also face challenges related to social exclusion and safety, requiring a balance between promoting community integration and ensuring public safety. This study offers valuable insights for the development of pet parks, the creation of vibrant and diverse public spaces, and the promotion of harmonious human-animal environments in cities across China and other Asian countries.

● Applies the spatial justice theoretical framework to the study of pet parks in an Asian city for the first time

The construction of a barrier-free environment is an important measure that guarantees the safety, right-of-way, and interests of the disabled, the elderly, and other mobility disadvantaged groups. It is also an indispensable part of the low-carbon urban transportation and a necessary way to protect the rights of mobility disadvantaged groups in green travel. In this paper, the researchers conducted life log surveys on the travels of 10 wheelchair users residing in Beijing with IoT Inspector, a self-developed, wheelchair-mountable intelligent sensing device. Wheelchair users' travel preferences and reasons were then analyzed using the image and textual data from the surveys. Combined with a mapping workshop, a comparative analysis was performed on the bumpiness of sidewalk paving materials. The study found that wheelchair travelers' preferred non-motor lanes over sidewalks; substandard curb ramps, unleveled tree pools, limited access widths, and bumpy pavement were the main problems faced by wheelchair users in sidewalk accessibility. In addition, the study explores the inclusive needs and challenges of non-motorized right-of-way for new transportation means at urban planning and traffic management levels. Based on multi-sourced data, this paper discusses the possibility of assessing urban barrier-free environment and representing a narrative of the needs of mobility disadvantaged groups, so as to provide practical experience and technical support to the improvement strategies of adaptive roads.

This research investigated the impact of social-networking service posts on the formation of image structure of cities, focusing on the spatial distribution of images and their content similarity. It aimed to delineate the image structure of cities created by numerous users, moving beyond traditional qualitative methods towards a more quantitative and objective approach with big data. Taking central Tokyo as an example, this study extracted geotagged image data of 33 major railway station areas from Flickr's API (Application Programming Interface). Four coverage types of viewpoint distribution, namely planar, intersecting linear, linear, and nodal, were identified, reflecting the unique urban structures respectively. Further investigation of the image contents, primarily consisting of "urban landscape" and "landscape/street trees, " showed that such contents significantly influenced the formation of the image structure of cities. The study concluded that as the number of photo posts increased and the representative viewpoints concentrated, the digital information received by users became more homogeneous, leading to strongly stereotyped images of urban landscapes. These findings highlight the role of social networking services in shaping perceptions of the urban environment and provide insights into the image structure of cities as formed by digital information.

As important cultural service providers in urban ecosystems, historical blocks play a crucial role in ensuring the well-being of multiple stakeholders during the urban renewal process. Based on theories of Landsenses Ecology and literature review, this study systematically examined the landsense elements of historical blocks and their related cultural ecosystem services (CES) by proposing a landsense design practice framework for CES enhancement and further constructing a landsense evaluation indicator system. Using the Three-Lanes and Seven-Alleys Block in Fuzhou, China as a case study, this research analyzed the status quo and existing problems of the block according to the evaluation indicator system, and then proposed suggestions for landsense creation to enhance, preserve, and improve CES of the block. Finally, it qualitatively elaborated the evaluation indicators upon the practice framework of landsense design. This study provides an essential theoretical foundation and evaluation basis for enhancing CES in historical blocks from a perspective of multi-dimensional perceptions.

As an extension of environmental justice, landscape justice emphasizes achieving inclusive and equitable planning and design in both built and natural environments, allowing different social groups to enjoy and share landscape resources and benefits more equally. By endowing landscape design with a “just” orientation, landscape justice significantly improves the spatial and environmental benefits while promotes the process of environmental justice. Landscape justice is characterized by its interdisciplinary nature, showing great variability in spatio-temporal scales, site dimensions and attributes, and social groups and scenarios, the research of which urgently requires in-depth dialogues, sincere collaborations, and active explorations among multiple disciplines. We call for enriching the connotation of landscape justice through interdisciplinary perspectives and addressing practical issues, to provide innovative spatial propositions and paths for creating sustainable urban environments and landscapes.

Urban green spaces contribute to improving people's physical and mental health by reducing levels of stress and anxiety. Marginalized communities in the USA experience poor health outcome in part because of health disparities related to social and structural determinants of health. The purpose of this study is to assess the prospective role of Kellogg Park, a newly built community park in a marginalized community in California, in enhancing residents' physical and mental health. The researchers collected the data by conducting an in-person survey, which covered questions related to environmental and safety perceptions, overall satisfaction, changes in physical activity changes and mental health with respondents' pre- and post-occupancy experiences. For analyzing data, bivariate analyses using a t-test and a correlation analysis were conducted to examine if there was a relationship between the overall satisfaction and visiting experience. The results indicated an increased positive environmental perception. Besides, respondents reported positively to questions of safety and their overall satisfaction. This research yielded positive results, indicating an improvement in the respondents' physical activity changes and mental health after the construction of the park. The results will advocate for and assist planners, designers, and policy-makers in prioritizing green spaces in marginalized communities.

● Reveals that increased physical and mental health was closely related to the accessibility of urban green spaces

Combining research methods such as semantic analysis and Space-Time Cube, this paper proposes a "historic urban landscape–cognition–sentiment" analysis framework, covering aspects of heritage intrinsic value, urban functional value, and urban landscape value, and reveals the influencing mechanism of the characteristics of historic urban landscape (HUL) on public sentiments and the spatio-temporal differentiation patterns through the case study of the Shaoxing ancient city in China. The research findings include that different HUL characteristics had differentiated effects on public sentiments, and the effect of a same HUL characteristic on public sentiments varied between weekdays and weekends/holidays, and among different HULs. On weekends/holidays, public sentiments were more influenced by the intrinsic value factors of HUL (e.g., heritage level, heritage age), whereas on weekdays, they were more affected by urban functional value factors, and urban landscape value factors played a greater role in arousing people's positive sentiments. This study aims to provide scientific references for enhancing public perception and emotional experience in urban spaces and for identifying potential spatial improvement opportunities in historic cities.

● Innovatively proposes "HUL–Cognition–Sentiment" analysis framework, and systematically explores the influencing mechanism of HUL characteristics on public sentiments

The establishment and development of the Guangdong–Hong Kong–Macao Greater Bay Area have demonstrated the collaborative relationship of the globally regional reconstructing. As a major strategy of the Greater Bay Area, Northern Metropolis faces challenges in transboundary ecological collaborative management. Based on the analysis of the ecological issues and the complexity of the transboundary management in Shenzhen Bay, this article proposes a co-governed “Special Ecological Conservation Zone” under the context of “one country, two systems” by zoning areas with varied protection levels. The development and operation framework includes: establishing an independent Joint Work Group, building consensus and standardizing collaboration procedure, conducting hierarchical management and regulating development, leveraging and motivating knowledge and technological innovation, and strengthening community engagement and emphasizing shared benefits. By case-studying three sites along the Shenzhen Bay, this article also provides place-making strategies for different levels of protection zones. Exploring innovative collaboration models for Northern Metropolis, this article is expected to provide new solutions for the sustainable development of the Greater Bay Area and creative insights for global transboundary ecological collaborative management.

With the continuous advance of big data and artificial intelligence technologies, various data-driven machine learning algorithms have been widely applied in the studies of urban resilience, particularly in addressing the challenging issue of urban waterlogging. Currently, it is a pressing task to understand the influencing factors of waterlogging from the perspective of built environment, and provide guidance on dynamic monitoring and early alarm services. Focusing on Shenzhen, China, a typical high-density urbanized city, this research constructed a multifactorial dataset encompassing hydrological, meteorological, urban morphology, and waterlogging event data. Then, this research assessed and compared the performance of four mainstream machine learning models—LightGBM, RF, SVR, and BPDNN—in predicting urban waterlogging risks. The results showed that LightGBM had the best accuracy and robustness in predicting waterlogging depths and risk levels in urban areas. The research also employed interpretability algorithm—Shapley Additive Explanations (SHAP)—for decoupling analysis. The results indicated that hydro-meteorological factors (the total rainfall volume and the rainfall lasting time) and several architectural configuration factors (e.g., density of buildings, building congestion degree) are the main influencing factors. In addition, the percentage of water body is vital to waterlogging regulation and retention, especially exhibiting a significant mitigating effect when exceeding 2.5%. This research provides a new technical method for urban waterlogging prediction and reveals the influencing factors and intrinsic mechanisms from the perspective of built environment, which is of great significance for the enhancement of the resilience of high-density cities.

The Niagara Escarpment, a 440-million-year-old landform, cuts through a property owned by the University of Toronto in Caledon, Ontario in Canada. The property juxtaposes impacts from historical quarrying activity which burrowed directly into the Escarpment’s slope, the greater context of the region’s urban development demands, and the Escarpment’s identity as an ancient geological formation, ecological refugium, and old-growth forest housing ancient species such as Thuja occidentalis.

This project explores the university’s responsibility in advocating for the protection of the Escarpment’s unique ecologic conditions, including the distinct cliff ecosystems and the novel successional plant communities evolving on sites of former quarry activities. Interventions on the trail system, cave bridges and lookouts, and the boardwalk and path system, along with guidance of signage and trail markers, will bring visitors to areas where former quarry activities sculptured the Escarpment’s limestone faces and are now reclaimed by a system of lush novel wetlands and habitats in evolutionary stages. Connecting to a system of existing public trails, this project leverages the university’s educational and recreational objectives to form new strategic partnerships with local conservancy groups, aiming at monitoring and managing access and habitat protection.

● Indigenous-led conservation efforts and partnerships with local conservancy groups are emphasized to enhance sustainability and stewardship

The research on the impact of urban blue spaces on residents' mental health has attracted great attention from scholars internationally, and quantitative studies of the effects dominate the current academia. This study, on the basis of reviewing the theories of urban blue spaces and residents' mental health, conducted a meta-analysis of 47 key studies by systematically selecting and examining the literature from Web of Science, CNKI, and other databases. This paper analyzed the measuring indicators and research models among the literature and standardized the effect size of the research findings. The meta-analysis results include that: 1) the measurements of the characteristics of urban blue spaces are mainly conducted in space-based and individual-based dimensions; 2) residents' mental health is mainly measured from aspects of general mental health, positive psychology, and negative psychology; 3) the proximity of blue space has a significant positive effect in improving residents' general mental health and positive psychology; 4) the availability of blue space is significantly positively correlated with general mental health and positive psychology; 5) although there are studies confirming that factors such as blue space visibility, frequency of visit, and exposure types have an impact on mental health, the relevant studies are still limited; and 6) research on the effect of blue spaces on negative psychology is controversial, especially on mental disorders such as depression, and the findings among existing studies vary significantly. The results of this meta-analysis can provide guidelines for future research and the construction of healthy cities.

Facing challenges of population decline and fiscal austerity, Japan has implemented a series of initiatives to promote public-private partnerships (PPP) to ensure the sustainability of urban parks and revitalize urban spaces. These initiatives, while alleviating the government's financial burdens on parks, have also raised concerns about the potential erosion of publicness and public interests resulted from the commercialization of public assets. This paper reviews the evolution of Japan's urban park management system after World War Ⅱ—including three phases of being purely public goods, initiating marketization, and diversifying management entities. The functions of parks have continuously enriched, and the construction, management, and operational modes have shifted from government-led towards multi-stakeholder participation, along with expanded funding sources. By examining the PPP types, driving forces, implementation mechanisms and challenges in urban park management, this paper points out that, in different eras and social contexts, the Japanese government has kept adjusting its role to maximize public interests. This has proactively updated the implications of publicness in infrastructure like urban parks, from a post-war opposite of publicness versus privateness on ownership, to the participation of private capital for a higher efficiency, and finally to a community for a stronger regional competitiveness. The reforms of urban park management system in Japan offer significant lessons and insights for urban infrastructure management in other countries and regions.

● Proposes that the evolution of Japan's urban park management system has undergone three phases: being purely public goods, initiating marketization, and diversifying management entities

The Vatican Climate Summit, titled “From Climate Crisis to Climate Resilience”, was successfully held in May 2024. A landmark achievement of the Summit was the introduction and adoption of the Planetary Protocol for Climate Change Resilience. This comprehensive framework calls for global cooperation to enhance climate resilience through the implementation of the MAST principles—mitigation, adaptation, and societal transformation, laying the groundwork for a strategic approach to climate action. Facing the current climate challenge, it is also crucial to understand the complexity of climate change, conduct climate design, and promote educational paradigm change for future global leadership in planet stewardship.

In recent years, the convergence of accelerating climate change, land use changes, and modified fire regimes has escalated the risk of catastrophic wildfires. In response, landscape stewardship tools such as the application of beneficial fire are being increasingly employed worldwide to mitigate fuel accumulation, improve habitat, and support eco-cultural practices. Beneficial fire encompasses various forms, including cultural burns, prescribed burns, or simply allowing naturally-occurring wildfires to safely burn out. Historically, those involved in planning and designing landscapes have resisted the transformative power of fire by embracing spatial techniques that suppress and push fire away. However, this article highlights co-creative strategies that embrace and utilize pyric forces. It discusses how landscape architects can broaden their wildfire adaptation toolbox to incorporate land-fire stewardship techniques. The article also acknowledges the agency of landscape architects to pursue (or not pursue) projects in fire-prone areas, promotes collaboration with existing fire stewards to gain insights and include them as key members of project teams, and explores how landscape architects could become active stewards themselves.

● The risks and negative impacts of wildfire are intensifying globally

Exploring the scale-effect of different land use types on the distribution pattern of urban park green space (PGS) at multiple grid scales would inform rational allocation and efficient collaborative construction of urban development land at different scales. Selecting 300-m, 500-m, 1, 000-m, and 2, 000-m grid scales, the research employed Create Fishnet tool in ArcGIS and Geodetector to construct a scale-effect analysis framework that revealed the scale-effects of different land use types on the distribution pattern of PGS at multiple grid scales in the main urban area of Nanjing, China in 2006, 2012, and 2017. Main research results are: 1) the overall distribution pattern of PGS showed the evolution characteristics from polarization to advancing quality and efficiency, while the trend gradually weakened with the increase of grid scale; 2) the scale-effect of other land use types on PGS increasingly enhanced—the larger the grid scale, the more obvious the synergistic or compressive effect; 3) the interactive scale-effects of different land use types gradually enhanced—the larger the grid scale, the more significant the overall factor interaction; and 4) at the 300-m grid scale, the major interaction factors were residential, transportation, industrial/manufacturing, water area, and administration/public services, which gradually changed to residential, water area, and administration/public services up to the 2, 000-m grid scale. The findings of this paper are expected to deepen the theory of the coupling between PGS and other land use types, as well as provide scientific support and a basis for efficient allocation, spatial layout optimization, and sustainable development of urban spaces.

Visual quality assessment of urban green spaces is a major topic in landscape architecture research, yet traditional methods face limitations in practice. The rapid development of artificial intelligence and street-view big data offers opportunities for advancing green space perception studies. However, the lack of full street view image coverage of green spaces in China poses challenges for related research. Focusing on public landscape perception evaluation, this research took Zhujiang Park in Guangzhou, China as a case study. The research team utilized a convenient image collection method by panoramic camera and an effective processing workflow, and then employed the Segformer-B5 semantic segmentation model and the ViT-base-p16 image classification model to calculate four objective evaluation metrics (green view index, sky view factor, road visibility index, and artificial structure visibility index) and four subjective evaluation metrics (attractiveness, richness, naturalness, and depression) for visual quality assessment. Based on the spatial distribution results of these metrics, comprehensive analyses were conducted and low-score areas were identified. Research results indicate that vegetation and water features significantly enhance park attractiveness and positive perceptions, while excessive sky and artificial structures produce negative effects; oppressive artificial landscapes and constrained architectural views also lower overall landscape quality. The image collection and visual perception evaluation methods proposed in this study provide a scientific basis for the renovation and management of urban green spaces.