Landscape and Urban Planning最新文献

{"title":"Exploring the potential of generative AI to complement multi-stakeholder landscape preference assessment","authors":"Jingya Lin ,&nbsp;Chongzhi Chen ,&nbsp;Tian Feng ,&nbsp;Sigao Huo ,&nbsp;Kexin Zhang ,&nbsp;Baiyu Dong ,&nbsp;Shanshan Xiang ,&nbsp;Ke Wang ,&nbsp;Lu Huang","doi":"10.1016/j.landurbplan.2026.105602","DOIUrl":"10.1016/j.landurbplan.2026.105602","url":null,"abstract":"<div><div>As urbanization and agricultural intensification continue to reshape rural landscapes, understanding and incorporating diverse stakeholder preferences has become crucial for sustainable land use and management. Traditional landscape preference assessments remain constrained by limited scalability, high cost, and time intensity, highlighting the potential of artificial intelligence to complement human evaluation. This study employs two multimodal large language models (MLLMs), GPT-4o and Qwen3, to simulate and analyze the landscape preferences of farmers, tourists, and experts in the Mulberry-Dyke and Fish-Pond agricultural landscape in China. Extreme gradient boosting and Shapley additive explanations were applied to examine discrepancies between MLLMs’ predictions and human judgments, and to examine how specific landscape characteristics shape stakeholder preferences. Furthermore, stakeholder-derived importance weights of landscape characteristics were incorporated into the prompts to improve model alignment with human perception. The results show that GPT-4o outperformed Qwen3 in predicting human preferences. While humans emphasized the dyke-pond ratio and fishpond shape, GPT-4o tended to prioritize built-environment features such as local buildings. Incorporating stakeholder evaluations into the prompting process substantially enhanced model-human correlation by approximately 38%, 85%, and 54% for farmers, tourists, and experts, respectively. These findings demonstrate that MLLMs can serve as adaptive tools for multi-stakeholder landscape preference evaluations, offering new opportunities to integrate diverse human perspectives into landscape planning and decision-making.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105602"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative artificial intelligence use in automated urban ecological assessments requires substantial human oversight","authors":"Daniel Richards ,&nbsp;David Worden ,&nbsp;Sandra Lavorel","doi":"10.1016/j.landurbplan.2026.105615","DOIUrl":"10.1016/j.landurbplan.2026.105615","url":null,"abstract":"<div><div>Automated data processing pipelines and generative artificial intelligence (AI) present new opportunities for scaling ecological assessments across urban areas, yet the practical utility and limitations remain untested. This study provides a workflow for automated urban ecological reporting, which integrates 25 public datasets and performs statistical and spatial data analyses to quantify indicators of biodiversity and ecosystem services. The workflow incorporates large language models to aid synthesis and writing. Reports were generated for diverse cities worldwide and reviewed by domain experts to assess quality, trust, and potential to inform urban planning. Respondents found that while the structure and data integration had potential to be helpful, the draft reports required substantial human revision. Factual sections relying on high-quality datasets needed the fewest changes, whereas content based heavily on AI inference, such as descriptions of climate change adaptation options, were inaccurate, generic, or culturally inappropriate. Despite these limitations, participants generally viewed the reports as potentially helpful. Of the total labour required to create reports, respondents estimated that around 10% could be substituted by automation. Our findings suggest that AI-assisted automated report generation may be scaled up to support urban sustainability efforts, but only with strong human oversight and transparent disclosure of AI use. Trust in automated assessments depends on transparency, and the inclusion of local voices in legitimising final outputs. Even with automation, substantial investment in human labour will be required to make ecological assessments available for towns and cities around the world.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105615"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147329979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perceiving agricultural heritage: How landscape attributes shape visual preferences—A case study in Iran","authors":"Atefeh Ansari,&nbsp;Mehri Motaharirad","doi":"10.1016/j.landurbplan.2026.105612","DOIUrl":"10.1016/j.landurbplan.2026.105612","url":null,"abstract":"<div><div>In the context of significant agricultural landscape changes, understanding public visual preferences is essential for landscape planning and conservation of these historical landscapes. This study evaluated the impact of landscape attributes on visual perceptions of historic agricultural landscapes in semi-arid regions, exemplified by the Isfahan Plain in Iran. Using linear mixed models, we investigated how ratings of pleasantness and the visual concepts from the framework developed by <span><span>Tveit, Ode, and Fry (2006)</span></span> —stewardship, coherence, disturbance, visual scale, imageability, complexity, and naturalness— were affected by landscape attributes and socio-demographic factors. Results indicate that physical attributes mainly shape visual evaluations, with moderate vegetation and traditional features such as earthen boundaries and dovecotes receiving the highest appreciation. Individual experience with agriculture and exposure to dovecotes also positively influenced perceptions, while demographic variables such as gender or residence in the Isfahan Plain showed limited impact. The findings highlight the importance of preserving traditional landscape elements and suggest that promoting public awareness and experiential engagement can support sustainable management and conservation of these heritage landscapes, informing policies for landscape planning and heritage preservation in similar arid and semi-arid regions.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105612"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147330203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding process differences in the impact of built–natural environments on compound heat–flood risks through urban physical characteristics","authors":"Kaiping Wang ,&nbsp;Chengbin Xi ,&nbsp;Xin Liu ,&nbsp;Lifu Zheng ,&nbsp;Yunlu Zhang","doi":"10.1016/j.landurbplan.2026.105599","DOIUrl":"10.1016/j.landurbplan.2026.105599","url":null,"abstract":"<div><div>Compound urban heat–flood risks are becoming a critical challenge for sustainable urban development. However, most existing studies focus only on surface-level analyses of how built and natural environments affect these risks, neglecting the intermediary transmission process. This study develops a multi-level analytical framework that incorporates urban physical characteristics as key mediators. Using Beijing’s high-density district as a case study, we first reveal an asymmetric causal relationship where heat risk exacerbates flood risk. The results of the cascading effect show that surface hardening shows a stronger direct effect on risk than ventilation cost, yet the built–natural environment generates a larger overall impact through ventilation cost. Specifically, natural environment pattern slightly reduces heat (−0.052) and flood risk (−0.047) by influencing ventilation. Natural environment configuration reduces heat (−0.332) and flood risk (−0.452), with 77.4% and 85.6% of the effects mediated by surface hardening. By contrast, the vertical built environment increases both heat and flood risk (0.218), with 75.7% and 63.3% of the effects mediated by ventilation cost. The horizontal built environment further amplifies risk by increasing both surface hardening (0.241) and ventilation cost (0.160). Finally, by leveraging the mediating effects of physical processes, we identify ventilation-dominated areas, hardening-dominated areas, and low-risk areas, and propose differentiated management strategies accordingly. This study confirms a multi-level transmission mechanism of “built–natural environment → urban physical characteristics → heat–flood risks” and underscores the importance of physical processes as mediators. The proposed framework demonstrates applicability and offers insights for urban risk research.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105599"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146777789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Linking window-view nature exposure with health and wellbeing outcomes: Using photorealistic 3D city models and computer vision technique","authors":"Dongwei Liu ,&nbsp;Di Wei ,&nbsp;Hung Chak Ho ,&nbsp;Maosu Li ,&nbsp;Yi Lu","doi":"10.1016/j.landurbplan.2026.105601","DOIUrl":"10.1016/j.landurbplan.2026.105601","url":null,"abstract":"<div><div>It is well established that nature exposure can improve both physical and mental health and wellbeing outcomes. However, in the context of rapid urbanization and high-density urban development, many urban residents face limited opportunities to visit natural environment, such as urban parks, greenways, and water bodies. In such situations, window view often serves as the primary means of people’s nature exposure. Traditional methods of assessing window-view nature exposure are time-consuming and labor-intensive, thus impractical for citywide evaluations. This study used a novel approach to quantify citywide assessment of window-view nature exposure, including the Window Greenery Index (WGI), Window Water Index (WWI), and Window Sky Index (WSI), using photorealistic 3D city models. We further analyzed the non-linear associations between window-view nature exposure with physical and mental health and wellbeing among 1,660 participants in Hong Kong for two periods: before and during the COVID-19 pandemic. For comparison, street-level nature exposure was also assessed. The result illustrates spatial mismatch between window-view and street-view nature exposure. Furthermore, window-view nature exposure had a greater influence than street-view nature exposure on physical and mental health and wellbeing. Furthermore, the effect of window-view nature exposure becomes more pronounced during the COVID-19 pandemic than before the pandemic. The results shed light on the link between window-view nature exposure and health and wellbeing outcomes, providing a new research front to understand the joint impacts of urban planning (i.e., provision of green space) and architectural design (i.e., location and orientation of windows) on public health.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105601"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146777787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bird feeders and rat traps: Understanding the relationships among psychosocial factors, wildlife observations, and yard management decisions","authors":"Nikolas Ballut ,&nbsp;Andrés M. Urcuqui-Bustamante ,&nbsp;Emily Minor","doi":"10.1016/j.landurbplan.2026.105603","DOIUrl":"10.1016/j.landurbplan.2026.105603","url":null,"abstract":"<div><div>Residential yards and gardens provide a multitude of benefits for people, including green infrastructure, access to nature, and improved mental health. Yards can also benefit wildlife by providing habitat, food and other resources. Previous studies have shown that people manage their gardens in different ways to attract or deter wildlife and that visible wildlife diversity can increase people’s investment in nature and resource provisioning. These relationships between people and wildlife could form feedbacks with long-term consequences for biodiversity, but the way that various factors, including observations and perceived presence of wildlife in residential gardens, affect people’s management decisions remains largely unexplored. To understand how these relationships shape yard management decisions, we organized and synthesized existing international scientific literature on wildlife gardening, identified major gaps in current knowledge, and suggest directions for future research that could improve our understanding of the dynamic, potentially reciprocal relationships between residents, their gardening behaviors, and wildlife. We identified 53 relevant studies from North America, South America, Europe, Oceania, Africa, and Asia. Most studies employed a qualitative approach to examine how attitudes toward wildlife influenced gardening behavior, with other determinants of wildlife gardening relatively understudied in the context of this literature search. Only five studies directly asked residents about wildlife observations or perceived presence of wildlife on their properties and related those observations to attitude or actual yard management behavior. For future research, we suggest that researchers measure multiple determinants of yard management decisions and conduct experimental and longitudinal studies to improve our understanding of the feedback loops between people and wildlife in residential landscapes.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105603"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surveying the scene: A review of how landscapes are valued","authors":"Andrés Pazmiño ,&nbsp;Edward A. Morgan ,&nbsp;Aysin Dedekorkut-Howes ,&nbsp;Michael Howes","doi":"10.1016/j.landurbplan.2026.105605","DOIUrl":"10.1016/j.landurbplan.2026.105605","url":null,"abstract":"<div><div>Planning theory and practice has placed considerable attention on the conservation of ecologically and culturally significant landscapes (ECSLs). A broad range of valuation systems have been proposed and implemented. This study performed a systematic literature review of 112 articles addressing the valuation of ECSLs to identify the landscape features that are most valued and why. The findings indicate that planning theorists and practitioners tend to follow material valuation approaches that prioritise the conservation and management of tangible landscape values. This trend has been traditionally driven by research and practice based in Europe, North America, Australia and Japan, and more recently from China. It follows more structured valuation systems such as the ecosystems services approach proposed by many international frameworks. In contrast, local landscape users assign value to landscape features depending on context-based experiences and aspirations that are underpinned by non-material valuation systems. The consideration of such intangible values could determine the extent to which stakeholders engage in landscape conservation. There is a need to develop more comprehensive valuation systems that can accommodate both material and non-material landscape values.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105605"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146778639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Social media big data reveals how mobility reshapes human environmental exposure inequality","authors":"Yan Zhang ,&nbsp;Mei-Po Kwan ,&nbsp;Haoran Ma ,&nbsp;Libo Fang ,&nbsp;Zeqiang Chen ,&nbsp;Nengcheng Chen","doi":"10.1016/j.landurbplan.2026.105600","DOIUrl":"10.1016/j.landurbplan.2026.105600","url":null,"abstract":"<div><div>For a long time, environmental exposure is considered closely related to people’s socioeconomic status (SES). Assessing this hypothesis seemed straightforward, as we could calculate the accessibility of green spaces around the residences of different socioeconomic groups, naturally concluding that high-SES residents enjoy higher green exposure. However, this assessment method relies on static residence-based evaluations without considering people’s daily mobility. In this study, we utilized over 100 million real activity locations and 1 million street view images to measure the mobility-based green exposure of approximately 20,000 users. We found that compared to the mobility-based green exposure, traditional residence-based assessments overestimate green exposure by 11.26% and green exposure inequality by as much as 54.44% (with the Gini coefficient decreasing from 0.5163 to 0.3343). The primary driver of changes in green exposure inequality is the reduction of within-group disparities. Further, after considering users’ mobility behavior, although high-income groups still experience higher levels and equality of green exposure compared to low-income groups, the relative gap in green exposure narrowed to 4.27%. This change is even more pronounced between cities, with the relative difference in green exposure between small and large cities shrinking from 32.70% to 16.83%. This study marks the first large-scale application of human mobility in environmental exposure research, significantly advancing our understanding of environmental exposure and inequality. The findings challenge long-standing conclusions in green exposure inequality studies, demonstrating that urban green exposure equity is higher than traditionally perceived. These results are also likely to be applicable to research on other similar environmental exposure issues.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105600"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Walking through history: The legacy of HOLC maps and urban walkability","authors":"Haoluan Wang,&nbsp;Guimin Zhu","doi":"10.1016/j.landurbplan.2026.105604","DOIUrl":"10.1016/j.landurbplan.2026.105604","url":null,"abstract":"<div><div>Proximity-based urban models have gained growing global attention in the past decade, emphasizing walkability and the promotion of urban resilience through localized living. Understanding neighborhood walkability is essential for advancing urban health, sustainability, and equity. In this study, we integrate a historically significant place-based policy in the U.S—the Home Owners’ Loan Corporation (HOLC) maps—with the Environmental Protection Agency’s Walkability Index to conduct the first nationwide assessment of neighborhood walkability in relation to redlining. To provide a more granular understanding of the structural drivers behind walkability disparities, we further disaggregate the overall Walkability Index into its four key components, including intersection density, proximity to transit stops, employment mix, and employment-household mix. Our findings reveal that, compared to D-graded (hazardous) neighborhoods, A-graded (best) neighborhoods generally exhibit lower walkability, primarily due to a lack of mixed land uses for employment and occupied housing units. This pattern holds consistently across cities of varying sizes and regions in the nation. Our findings offer new insights into the intersection of historical redlining practices and contemporary urban land-use planning and further contribute to a deeper understanding of how place-based policies shape neighborhood walkability outcomes.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"270 ","pages":"Article 105604"},"PeriodicalIF":9.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146777788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variation characteristics and segment differences of urban heat exposure risk in continuous time series: A comprehensive synchronous comparison of daily and hourly scales","authors":"Junmao Zhang ,&nbsp;Xia Yao ,&nbsp;Meixia Lin ,&nbsp;Tao Lin ,&nbsp;Yuan Chen ,&nbsp;Wenhui Li ,&nbsp;Hongkai Geng ,&nbsp;Yicheng Zheng ,&nbsp;Zixu Jia ,&nbsp;Hong Ye ,&nbsp;Guoqin Zhang","doi":"10.1016/j.landurbplan.2026.105587","DOIUrl":"10.1016/j.landurbplan.2026.105587","url":null,"abstract":"<div><div>High spatiotemporal dynamics of heat hazard and population exposure within cities and the time-sensitive risk mitigation measures in precise urban sustainable management pose urgent needs for a comprehensive understanding of heat exposure risk (HER) patterns, while rare research has been devoted to revealing the exact temporal variability of HER. Here, utilizing 744 hour-by-hour HER maps covering one complete month (31 days) in Xiamen City, China, we investigated in detail the variation characteristics and segment differences of urban HER in period series (hourly scale) and date series (daily scale) from the perspective of both the whole city and basic spatial unit (250 m), especially providing an innovative summary of evident temporal scale effects in terms of basic dynamic patterns, quantitative variability, consistency of time series segmentation, and segment difference of HER. Overall, HER in Xiamen showed much stronger temporal variability at the hourly scale (<span><math><mrow><msubsup><mrow><mi>CV</mi></mrow><mrow><mi>mean</mi></mrow><mrow><mi>hourly</mi></mrow></msubsup><mo>=</mo><mn>0.3719</mn><mo>&gt;</mo><mn>0.0796</mn><mo>=</mo><msubsup><mrow><mi>CV</mi></mrow><mrow><mi>mean</mi></mrow><mrow><mi>daily</mi></mrow></msubsup></mrow></math></span>), which was more attributed to population exposure objectively. Based on the temporal segments from quantitative hierarchical clustering patterns and qualitative calendar and sunrise/sunset moments, a greater difference magnitude was found in period series despite that there were significant segment differences (p &lt; 0.001) in HER between both daytime–nighttime and holiday–weekday–weekend or day off–working day. Accordingly, the high temporal variability of HER overlooked previously, particularly the diurnal and even inter-hour variability within a day, deserves more attention from researchers and city managers.</div></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":"269 ","pages":"Article 105587"},"PeriodicalIF":9.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}