Sustainable Cities and Society最新文献_第6页

Microclimatic dynamics and hydrological patterns in urban heat islands - A comprehensive perspective 城市热岛的小气候动力学和水文模式——综合视角

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-25 DOI: 10.1016/j.scs.2026.107184

Nasim Sadra , Mohammad Reza Nikoo , Abolfazl Nazari Giglou , Amir H. Gandomi

Urban Heat Islands (UHIs) and their associated microclimatic variability significantly impact hydrological patterns, necessitating the accurate quantification of these effects for effective urban water resource management. This study synthesises research from the early 2000s to 2025 on the complex interactions between urban microclimates and hydrology, focusing on precipitation patterns, runoff, evapotranspiration, and water quality in UHI. The research examines various methodologies employed to study these interactions, including observational research, modelling approaches, and advanced technologies such as remote sensing and machine learning. While certain methods prove effective for specific aspects of UHI hydrology, their performance varies across urban contexts and climates. Machine learning techniques have shown promise in capturing microclimatic nuances, but challenges persist in data integration and model generalisation. This review makes a distinct contribution to literature by bringing together recent research with an introduction to the novel Hydrological Urban Heat Island (HUHI) framework. It extends beyond conventional UHI research by explicitly accounting for the interconnection between thermal-hydrological processes, which leads to a novel and integrated understanding of urban water systems. We also propose a novel methodology for related studies with a strategic application of remote sensing proxies, a unified classification technique for enhanced transferability between models, and a critical transition from correlation to causal inference. It is a comprehensive strategy in which the goal is to overcome present difficulties associated with reducing urban water hazards and support more efficient and cost-effective climate-resilient planning.

城市热岛及其相关的小气候变率显著影响水文模式，需要对这些影响进行精确量化，以实现有效的城市水资源管理。本研究综合了21世纪初至2025年对城市小气候与水文之间复杂相互作用的研究，重点关注城市热岛的降水模式、径流、蒸散发和水质。该研究考察了用于研究这些相互作用的各种方法，包括观测研究、建模方法以及遥感和机器学习等先进技术。虽然某些方法对城市热岛水文的特定方面证明是有效的，但它们的效果因城市环境和气候而异。机器学习技术在捕捉微气候细微差别方面显示出了希望，但在数据集成和模型泛化方面仍然存在挑战。本综述通过将最近的研究与介绍新颖的水文城市热岛（HUHI）框架结合起来，对文献做出了独特的贡献。它通过明确考虑热水文过程之间的相互联系，从而对城市水系统有了新的综合理解，从而超越了传统的城市热岛研究。我们还提出了一种新的相关研究方法，即策略性地应用遥感代理，统一分类技术以增强模型之间的可转移性，以及从相关性到因果推理的关键转变。这是一项综合战略，其目标是克服目前与减少城市水害有关的困难，并支持更有效和更具成本效益的气候适应型规划。

{"title":"Microclimatic dynamics and hydrological patterns in urban heat islands - A comprehensive perspective","authors":"Nasim Sadra , Mohammad Reza Nikoo , Abolfazl Nazari Giglou , Amir H. Gandomi","doi":"10.1016/j.scs.2026.107184","DOIUrl":"10.1016/j.scs.2026.107184","url":null,"abstract":"<div><div>Urban Heat Islands (UHIs) and their associated microclimatic variability significantly impact hydrological patterns, necessitating the accurate quantification of these effects for effective urban water resource management. This study synthesises research from the early 2000s to 2025 on the complex interactions between urban microclimates and hydrology, focusing on precipitation patterns, runoff, evapotranspiration, and water quality in UHI. The research examines various methodologies employed to study these interactions, including observational research, modelling approaches, and advanced technologies such as remote sensing and machine learning. While certain methods prove effective for specific aspects of UHI hydrology, their performance varies across urban contexts and climates. Machine learning techniques have shown promise in capturing microclimatic nuances, but challenges persist in data integration and model generalisation. This review makes a distinct contribution to literature by bringing together recent research with an introduction to the novel Hydrological Urban Heat Island (HUHI) framework. It extends beyond conventional UHI research by explicitly accounting for the interconnection between thermal-hydrological processes, which leads to a novel and integrated understanding of urban water systems. We also propose a novel methodology for related studies with a strategic application of remote sensing proxies, a unified classification technique for enhanced transferability between models, and a critical transition from correlation to causal inference. It is a comprehensive strategy in which the goal is to overcome present difficulties associated with reducing urban water hazards and support more efficient and cost-effective climate-resilient planning.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107184"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring diurnal spatiotemporal heterogeneity in urban heat exposure: A novel perspective from urban form-function coupling 探索城市热暴露的日时空异质性：从城市形式-功能耦合的新视角

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-14 DOI: 10.1016/j.scs.2026.107161

Aihemaiti Namaiti , Suiping Zeng , Weijie He , Xiang Liu , Jian Zeng

Understanding the spatiotemporal heterogeneity of diurnal urban heat exposure is crucial for addressing urban heat governance challenges. However, most studies focus on either urban form or function, lacking an integrated perspective to fully capture heat exposure heterogeneity. This study, using Nanchang, a typical Chinese “furnace city,” as a case study, proposes a novel form-function coupling framework. Through K-means clustering’s flexibility and local adaptability, it divided the study area into 12 homogeneous form-function clusters. By integrating high-resolution ECOSTRESS LST and mobile signaling data, it assessed diurnal heat exposure levels and their heterogeneity with precision. The High-Risk Contribution Index (HCI) was introduced to quantify each cluster’s contribution to high heat exposure risk. Results showed that the 12 clusters, based on form-function coupling, exhibited distinct heat exposure patterns, effectively capturing urban heat exposure heterogeneity. Kruskal-Wallis H tests and post hoc multiple comparisons confirmed highly significant differences in heat exposure among clusters across all time points (H values 3713.242–4367.439, p<0.001), with 71.21 %–80.30 % of pairwise comparisons showing significant differences (p<0.05). Three contribution patterns emerged: (1) consistently high contribution (clusters 8, 9, 10, 11, 12; average HCI >2; high-density commercial and residential zones), requiring priority intervention; (2) consistently low contribution (clusters 1, 2, 3, 4; average HCI <0.6; ecological zones), needing protection to leverage their “cool source” role; and (3) diurnal variation (clusters 6, 7; daytime HCI >1, nighttime <1; influenced by industrial activity timing), requiring flexible interventions based on production schedules. These findings provide a replicable paradigm for precise, dynamic, and localized urban heat exposure governance and offer a theoretical-methodological framework for similar cities, enhancing the scientific rigor and practicality of heat governance strategies.

了解城市日热暴露的时空异质性对于解决城市热治理挑战至关重要。然而，大多数研究都集中在城市形态或功能上，缺乏一个完整的视角来充分捕捉热暴露的异质性。本研究以中国典型的“炉城”南昌为例，提出了一种新的形式-功能耦合框架。通过K-means聚类的灵活性和局部适应性，将研究区域划分为12个同质的形式-功能聚类。通过整合高分辨率ECOSTRESS LST和移动信号数据，该研究精确评估了日热暴露水平及其异质性。引入高风险贡献指数（HCI）来量化每个集群对高热暴露风险的贡献。结果表明，基于形式-功能耦合的12个集群表现出不同的热暴露模式，有效地捕捉了城市热暴露的异质性。Kruskal-Wallis H检验和事后多重比较证实，在所有时间点上，集群之间的热暴露差异非常显著（H值为3713.242-4367.439,p<0.001）， 71.21% - 80.30%的两两比较显示显著差异（p<0.05）。出现了三种贡献模式：(1)持续高贡献（集群8、9、10、11、12；平均HCI >2；高密度商业和住宅区），需要优先干预；(2)持续低贡献（集群1、2、3、4；平均HCI为0.6；生态区），需要保护以发挥其“冷源”作用；(3)日变化（集群6,7；白天HCI >；1，夜间HCI <1；受工业活动时间影响），需要基于生产计划的灵活干预。这些发现为精确、动态和本地化的城市热暴露治理提供了可复制的范例，并为类似城市提供了理论方法框架，增强了热治理策略的科学严谨性和实用性。

{"title":"Exploring diurnal spatiotemporal heterogeneity in urban heat exposure: A novel perspective from urban form-function coupling","authors":"Aihemaiti Namaiti , Suiping Zeng , Weijie He , Xiang Liu , Jian Zeng","doi":"10.1016/j.scs.2026.107161","DOIUrl":"10.1016/j.scs.2026.107161","url":null,"abstract":"<div><div>Understanding the spatiotemporal heterogeneity of diurnal urban heat exposure is crucial for addressing urban heat governance challenges. However, most studies focus on either urban form or function, lacking an integrated perspective to fully capture heat exposure heterogeneity. This study, using Nanchang, a typical Chinese “furnace city,” as a case study, proposes a novel form-function coupling framework. Through K-means clustering’s flexibility and local adaptability, it divided the study area into 12 homogeneous form-function clusters. By integrating high-resolution ECOSTRESS LST and mobile signaling data, it assessed diurnal heat exposure levels and their heterogeneity with precision. The High-Risk Contribution Index (HCI) was introduced to quantify each cluster’s contribution to high heat exposure risk. Results showed that the 12 clusters, based on form-function coupling, exhibited distinct heat exposure patterns, effectively capturing urban heat exposure heterogeneity. Kruskal-Wallis H tests and post hoc multiple comparisons confirmed highly significant differences in heat exposure among clusters across all time points (H values 3713.242–4367.439, p<0.001), with 71.21 %–80.30 % of pairwise comparisons showing significant differences (p<0.05). Three contribution patterns emerged: (1) consistently high contribution (clusters 8, 9, 10, 11, 12; average HCI >2; high-density commercial and residential zones), requiring priority intervention; (2) consistently low contribution (clusters 1, 2, 3, 4; average HCI <0.6; ecological zones), needing protection to leverage their “cool source” role; and (3) diurnal variation (clusters 6, 7; daytime HCI >1, nighttime <1; influenced by industrial activity timing), requiring flexible interventions based on production schedules. These findings provide a replicable paradigm for precise, dynamic, and localized urban heat exposure governance and offer a theoretical-methodological framework for similar cities, enhancing the scientific rigor and practicality of heat governance strategies.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107161"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessing the impact of industrial areas on land surface temperature: A comparison with urban and green spaces in the context of global warming 评估工业区对地表温度的影响：全球变暖背景下与城市和绿地的比较

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-27 DOI: 10.1016/j.scs.2026.107185

Asfra Rizwan Toor, Zubair Khalid

This study provides a comprehensive analysis of the urban heat island (UHI) effect and land surface temperature (LST) variations across Lahore, Pakistan, focusing on industrial, residential, and green spaces. Within the broader UHI framework, the study foregrounds the intra-urban heat island (IHI) phenomenon, which captures fine-scale thermal contrasts among industrial, residential, and green spaces. This perspective helps show how industrial growth creates localized hotspots in the urban environment. Using Landsat imagery, the split-window algorithm, and vegetation and built-up indices, the study tracks LST trends over 24 years (2000–2024). A comparative analysis of supervised classification algorithms and Otsu thresholding with K-means clustering was conducted to assess vegetation distribution, demonstrating the value of combining automated and supervised methods for improved land-cover assessment. Results reveal a clear industrial thermal footprint following the establishment of the industrial estate in 2007, with peak summer LST reaching 43.2

° C

at the core and declining to 41.6

° C

within a 5 km radius. A maximum temperature contrast (

Δ T_{max}

) of 3

° C

confirms localized heat accumulation. Residential areas show persistent warming, whereas green spaces consistently maintain the lowest LST. Vegetation loss is associated with an increase in LST of up to 4.6

° C

, underscoring the cooling role of green infrastructure. Despite peak rainfall of 905 mm in 2021, IA temperatures remained high, indicating that impervious surfaces limit precipitation-driven cooling. The study offers long-term empirical insight but is constrained by Landsat’s spatial resolution and the absence of socioeconomic or atmospheric pollution variables, which future work should integrate for a more holistic assessment. The study advocates for targeted nature-based interventions to reduce heat stress and enhance urban resilience.

本研究对巴基斯坦拉合尔的城市热岛效应和地表温度变化进行了综合分析，重点关注工业、住宅和绿地。在更广泛的城市热岛框架内，该研究突出了城市内部热岛现象，它捕捉到了工业、住宅和绿色空间之间的精细尺度的热对比。这一视角有助于展示工业增长如何在城市环境中创造局部热点。利用陆地卫星图像、分窗算法以及植被和建筑指数，该研究追踪了24年（2000-2024年）的地表温度趋势。对比分析了监督分类算法与Otsu阈值与K-means聚类对植被分布的影响，证明了自动化和监督相结合的方法在改进土地覆盖评估中的价值。结果表明，2007年工业园区建成后，工业热足迹明显，夏季温度峰值在核心地区达到43.2°C，在5 km半径范围内下降到41.6°C。最高温度对比（ΔTmax）为3°C，证实了局部热积累。住区持续升温，而绿地持续保持最低的地表温度。植被损失与地表温度升高高达4.6°C相关，强调了绿色基础设施的降温作用。尽管2021年降雨量达到905毫米的峰值，但IA温度仍然很高，这表明不透水的表面限制了降水驱动的冷却。该研究提供了长期的经验见解，但受到Landsat的空间分辨率和缺乏社会经济或大气污染变量的限制，未来的工作应该整合这些变量以进行更全面的评估。该研究提倡有针对性的以自然为基础的干预措施，以减少热应激和增强城市弹性。

{"title":"Assessing the impact of industrial areas on land surface temperature: A comparison with urban and green spaces in the context of global warming","authors":"Asfra Rizwan Toor, Zubair Khalid","doi":"10.1016/j.scs.2026.107185","DOIUrl":"10.1016/j.scs.2026.107185","url":null,"abstract":"<div><div>This study provides a comprehensive analysis of the urban heat island (UHI) effect and land surface temperature (LST) variations across Lahore, Pakistan, focusing on industrial, residential, and green spaces. Within the broader UHI framework, the study foregrounds the intra-urban heat island (IHI) phenomenon, which captures fine-scale thermal contrasts among industrial, residential, and green spaces. This perspective helps show how industrial growth creates localized hotspots in the urban environment. Using Landsat imagery, the split-window algorithm, and vegetation and built-up indices, the study tracks LST trends over 24 years (2000–2024). A comparative analysis of supervised classification algorithms and Otsu thresholding with K-means clustering was conducted to assess vegetation distribution, demonstrating the value of combining automated and supervised methods for improved land-cover assessment. Results reveal a clear industrial thermal footprint following the establishment of the industrial estate in 2007, with peak summer LST reaching 43.2 <span><math><mrow><mo>°</mo><mi>C</mi></mrow></math></span> at the core and declining to 41.6 <span><math><mrow><mo>°</mo><mi>C</mi></mrow></math></span> within a 5 km radius. A maximum temperature contrast (<span><math><mrow><mi>Δ</mi><msub><mrow><mi>T</mi></mrow><mrow><mo>max</mo></mrow></msub></mrow></math></span>) of 3 <span><math><mrow><mo>°</mo><mi>C</mi></mrow></math></span> confirms localized heat accumulation. Residential areas show persistent warming, whereas green spaces consistently maintain the lowest LST. Vegetation loss is associated with an increase in LST of up to 4.6 <span><math><mrow><mo>°</mo><mi>C</mi></mrow></math></span>, underscoring the cooling role of green infrastructure. Despite peak rainfall of 905 mm in 2021, IA temperatures remained high, indicating that impervious surfaces limit precipitation-driven cooling. The study offers long-term empirical insight but is constrained by Landsat’s spatial resolution and the absence of socioeconomic or atmospheric pollution variables, which future work should integrate for a more holistic assessment. The study advocates for targeted nature-based interventions to reduce heat stress and enhance urban resilience.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107185"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147398996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A circular disaster management framework for resilient cities 韧性城市的循环灾害管理框架

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-27 DOI: 10.1016/j.scs.2026.107189

Mojtaba Parsaee , Tarlan Abazari , Navid Nickdoost , Mohsen Goodarzi , Mehran Shahhosseini , Fariborz Haghighat

This study explores the integration of circular economy (CE) and life cycle strategies into disaster management to enhance urban resilience and address environmental sustainability. Climate-related disasters generate vast debris volumes that overwhelm waste systems, disrupt essential services, and incur significant social, economic, and environmental challenges. The prevailing linear practices prioritize rapid disposal over resource recovery, resulting in extensive landfilling and significant environmental footprints. In contrast, a CE approach offers sustainable alternatives through material recovery strategies such as reuse and recycling. However, CE integration in disaster management remains underdeveloped. Through a systematic literature review of studies from 1995 to 2025, this research studies disaster management practices and identifies barriers, opportunities, and enablers across technical, institutional, economic, and social domains for effective CE integration. The findings are synthesized to characterize a scientifically grounded, adaptive framework for circular disaster management. The framework unfolds in three stages: (1) developing an integrative decision-support system, (2) creating a comprehensive education and training platform, and (3) catalyzing institutional and business transformation and strengthening public-private partnerships. This framework systematically addresses technical, institutional, economic, and social barriers while leveraging identified opportunities to facilitate widespread adoption of CE principles across disaster management phases. This framework establishes a foundation for future research, policy development, and CE implementation in disaster contexts. Through this framework, the paper contributes to advancing sustainable disaster management and urban resilience, providing stakeholders with actionable guidance to drive systemic changes across multiple domains.

本研究探讨了将循环经济和生命周期战略整合到灾害管理中，以增强城市韧性和解决环境可持续性问题。与气候有关的灾害产生了大量的碎片，使废物系统不堪重负，扰乱了基本服务，并带来了重大的社会、经济和环境挑战。现行的线性做法优先考虑快速处置而不是资源回收，导致大量的填埋和显著的环境足迹。相比之下，环保方法通过材料回收策略，如再利用和再循环，提供可持续的替代方案。然而，在灾害管理方面的环境行政一体化仍然不发达。通过对1995年至2025年的研究进行系统的文献回顾，本研究研究了灾害管理实践，并确定了技术、制度、经济和社会领域的障碍、机会和促进因素，以实现有效的CE整合。这些发现被综合起来，以表征一个有科学依据的适应性循环灾害管理框架。该框架分三个阶段展开：(1)开发综合决策支持系统；(2)创建综合教育和培训平台；(3)促进制度和业务转型，加强公私伙伴关系。该框架系统地解决了技术、制度、经济和社会障碍，同时利用已确定的机会，促进在灾害管理阶段广泛采用环保原则。这一框架为未来在灾害背景下的研究、政策制定和行政执行奠定了基础。通过这一框架，本文有助于推进可持续灾害管理和城市韧性，为利益相关者提供可操作的指导，以推动多个领域的系统性变革。

{"title":"A circular disaster management framework for resilient cities","authors":"Mojtaba Parsaee , Tarlan Abazari , Navid Nickdoost , Mohsen Goodarzi , Mehran Shahhosseini , Fariborz Haghighat","doi":"10.1016/j.scs.2026.107189","DOIUrl":"10.1016/j.scs.2026.107189","url":null,"abstract":"<div><div>This study explores the integration of circular economy (CE) and life cycle strategies into disaster management to enhance urban resilience and address environmental sustainability. Climate-related disasters generate vast debris volumes that overwhelm waste systems, disrupt essential services, and incur significant social, economic, and environmental challenges. The prevailing linear practices prioritize rapid disposal over resource recovery, resulting in extensive landfilling and significant environmental footprints. In contrast, a CE approach offers sustainable alternatives through material recovery strategies such as reuse and recycling. However, CE integration in disaster management remains underdeveloped. Through a systematic literature review of studies from 1995 to 2025, this research studies disaster management practices and identifies barriers, opportunities, and enablers across technical, institutional, economic, and social domains for effective CE integration. The findings are synthesized to characterize a scientifically grounded, adaptive framework for circular disaster management. The framework unfolds in three stages: (1) developing an integrative decision-support system, (2) creating a comprehensive education and training platform, and (3) catalyzing institutional and business transformation and strengthening public-private partnerships. This framework systematically addresses technical, institutional, economic, and social barriers while leveraging identified opportunities to facilitate widespread adoption of CE principles across disaster management phases. This framework establishes a foundation for future research, policy development, and CE implementation in disaster contexts. Through this framework, the paper contributes to advancing sustainable disaster management and urban resilience, providing stakeholders with actionable guidance to drive systemic changes across multiple domains.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107189"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Urban village recognition based on multimodal data fusion with an interpretable graph neural network 基于多模态数据融合的可解释图神经网络城中村识别

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-02-01 DOI: 10.1016/j.scs.2026.107199

Zhenkang Wang , Nan Xia , Jiechen Wang

Recognition of urban villages (UVs) is of strategic importance for urban sustainable development. Existing studies mostly rely on visual information or statistics data, ignore the spatial relationship between regions and the complementarity of multimodal data, and lack the analysis of the importance of drivers. Therefore, this study integrates multimodal data, including remote sensing imageries, street view images, geographic big data, and building footprint data, and constructs both two- and three-dimensional features system that fuses visual perception, socio-economic factors, and urban morphology. A UV recognition model is developed using a graph neural network-based GraphSAGE with city blocks as graph nodes and spatial adjacencies as edges, and the GNNExplainer is introduced to analyze node importance and explain graph structure. Results showed 225 identified UVs totaling 61.4 km² in Nanjing, a representative high-density megacity in China, with an obvious ring-structured spatial distribution pattern containing 29.8 % in the core area. Recognition accuracy reached 97.2 %, which was 12.3 % and 5.1 % higher than the unimodal data and node ablation models on average, verifying the synergistic effect of visual, socio-economic, and morphological features, and the complementarity between self and neighbor node information. Cross-domain experiments in Changzhou and Suzhou cities identified 101 and 171 UVs with accuracies of 94.7 % and 92.4 %, demonstrating the model transferability. Moreover, explainability analysis revealed that high floor area ratio, high space congestion, high proportion of old buildings, and specific point-of-interest distribution patterns were typical UV characteristics. The proposed framework can provide efficient scientific support for urban planning and renewal decision-making.

对城中村的认可对城市可持续发展具有战略意义。现有研究大多依赖于视觉信息或统计数据，忽略了区域间的空间关系和多模态数据的互补性，缺乏对驱动因素重要性的分析。因此，本研究整合遥感影像、街景影像、地理大数据、建筑足迹数据等多模态数据，构建融合视觉感知、社会经济因素、城市形态的二维和三维特征体系。利用基于图神经网络的GraphSAGE，以城市街区为图节点，以空间邻接为边，建立了UV识别模型，并引入gnexplainer分析节点重要性，解释图结构。结果表明：南京是中国具有代表性的高密度特大城市，共鉴定出225个uv，总面积61.4 km²，具有明显的环形结构空间分布格局，核心区占29.8%；识别准确率达到97.2%，比单峰数据和节点消融模型平均高出12.3%和5.1%，验证了视觉、社会经济和形态特征的协同效应，以及自身和邻居节点信息之间的互补性。在常州和苏州的跨域实验中，分别识别出101和171个uv，准确率分别为94.7%和92.4%，表明了模型的可移植性。此外，可解释性分析表明，高容积率、高空间拥堵、高旧建筑比例和特定兴趣点分布模式是典型的紫外线特征。该框架可为城市规划和更新决策提供有效的科学支持。

{"title":"Urban village recognition based on multimodal data fusion with an interpretable graph neural network","authors":"Zhenkang Wang , Nan Xia , Jiechen Wang","doi":"10.1016/j.scs.2026.107199","DOIUrl":"10.1016/j.scs.2026.107199","url":null,"abstract":"<div><div>Recognition of urban villages (UVs) is of strategic importance for urban sustainable development. Existing studies mostly rely on visual information or statistics data, ignore the spatial relationship between regions and the complementarity of multimodal data, and lack the analysis of the importance of drivers. Therefore, this study integrates multimodal data, including remote sensing imageries, street view images, geographic big data, and building footprint data, and constructs both two- and three-dimensional features system that fuses visual perception, socio-economic factors, and urban morphology. A UV recognition model is developed using a graph neural network-based GraphSAGE with city blocks as graph nodes and spatial adjacencies as edges, and the GNNExplainer is introduced to analyze node importance and explain graph structure. Results showed 225 identified UVs totaling 61.4 km² in Nanjing, a representative high-density megacity in China, with an obvious ring-structured spatial distribution pattern containing 29.8 % in the core area. Recognition accuracy reached 97.2 %, which was 12.3 % and 5.1 % higher than the unimodal data and node ablation models on average, verifying the synergistic effect of visual, socio-economic, and morphological features, and the complementarity between self and neighbor node information. Cross-domain experiments in Changzhou and Suzhou cities identified 101 and 171 UVs with accuracies of 94.7 % and 92.4 %, demonstrating the model transferability. Moreover, explainability analysis revealed that high floor area ratio, high space congestion, high proportion of old buildings, and specific point-of-interest distribution patterns were typical UV characteristics. The proposed framework can provide efficient scientific support for urban planning and renewal decision-making.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107199"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Can nighttime light proxy comprehensive economic well-being? Evidence from China 夜间灯光能代表综合经济福利吗？来自中国的证据

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-29 DOI: 10.1016/j.scs.2026.107191

Wei Jiang , Jie Liu , Tengfei Long , Ming Liu , Akiyuki Kawasaki , Zhiguo Pang , Denghua Yan , Yizi Shang , Elhadi Adam , Xiaohui Ding , Shiai Cui

Although nighttime light data offer the potential for spatially measuring economic well-being (EWB) to achieve sustainable development goals, empirical validation remains insufficient. Fusion EWB of six representative Chinese counties (Yanshou, Bazhou, Yugan, Yongsheng, Wafangdian, Raoping) was analyzed using household surveys, statistical yearbooks, and entropy weight methodology—approaches that have proven more reliable than equal weight approaches for EWB calculation. The results revealed that (1) significant spatial heterogeneity exists between subjective and objective EWB across townships, demonstrating the necessity of fusion approaches; and (2) strong correlations exist between nighttime light and EWB—objective EWB (R²=0.801, p<0.001) and fusion EWB (R²=0.808, p<0.001)—validating nighttime light as an effective proxy indicator. This study first proposes and validates the fusion EWB concept, addressing the limitations of single-dimensional assessments while establishing the utility of nighttime light for EWB measurement. The methodology provides a scalable framework for spatial EWB simulation and sustainable poverty reduction assessment, offering crucial implications for sustainable urban–rural development planning and SDG monitoring in developing regions.

尽管夜间灯光数据为实现可持续发展目标提供了空间测量经济福祉（EWB）的潜力，但经验验证仍然不足。采用入户调查、统计年鉴和熵权法对中国六个具有代表性的县（延寿、霸州、余干、永胜、瓦房店、饶平）的融合EWB进行了分析，这些方法已被证明比等权法更可靠。结果表明：(1)主客观EWB存在显著的空间异质性，表明融合方法的必要性；(2)夜间灯光与EWB -客观EWB （R²=0.801,p<0.001）和融合EWB （R²=0.808,p<0.001）之间存在较强的相关性，验证了夜间灯光是有效的代理指标。本研究首次提出并验证了融合EWB概念，解决了单维评估的局限性，同时建立了夜间灯光对EWB测量的效用。该方法为空间EWB模拟和可持续减贫评估提供了可扩展的框架，对发展中地区的可持续城乡发展规划和可持续发展目标监测具有重要意义。

{"title":"Can nighttime light proxy comprehensive economic well-being? Evidence from China","authors":"Wei Jiang , Jie Liu , Tengfei Long , Ming Liu , Akiyuki Kawasaki , Zhiguo Pang , Denghua Yan , Yizi Shang , Elhadi Adam , Xiaohui Ding , Shiai Cui","doi":"10.1016/j.scs.2026.107191","DOIUrl":"10.1016/j.scs.2026.107191","url":null,"abstract":"<div><div>Although nighttime light data offer the potential for spatially measuring economic well-being (EWB) to achieve sustainable development goals, empirical validation remains insufficient. Fusion EWB of six representative Chinese counties (Yanshou, Bazhou, Yugan, Yongsheng, Wafangdian, Raoping) was analyzed using household surveys, statistical yearbooks, and entropy weight methodology—approaches that have proven more reliable than equal weight approaches for EWB calculation. The results revealed that (1) significant spatial heterogeneity exists between subjective and objective EWB across townships, demonstrating the necessity of fusion approaches; and (2) strong correlations exist between nighttime light and EWB—objective EWB (R²=0.801, <em>p<0.001</em>) and fusion EWB (R²=0.808, <em>p<0.001</em>)—validating nighttime light as an effective proxy indicator. This study first proposes and validates the fusion EWB concept, addressing the limitations of single-dimensional assessments while establishing the utility of nighttime light for EWB measurement. The methodology provides a scalable framework for spatial EWB simulation and sustainable poverty reduction assessment, offering crucial implications for sustainable urban–rural development planning and SDG monitoring in developing regions.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107191"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward greener, smarter, and more resilient cities: Assessing the impact of dual pilot policies of forest city and smart city on urban climate resilience in China 迈向更绿色、更智慧、更有韧性的城市：评估森林城市和智慧城市双试点政策对中国城市气候韧性的影响

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-15 DOI: 10.1016/j.scs.2026.107155

Yaobin Liu , Sheng Hu , Shuoshuo Li , Weifeng Deng

Climate risks threaten the sustainable development of urban economies, societies, and ecosystems. Urban climate resilience (UCR) is difficult to comprehensively improve through single policies. Forest cities and smart cities are typical examples of nature-based and technology-driven solutions, which have been extensively studied for their environmental impacts. However, it remains uncertain whether dual pilot policies (DPP) for forest cities and smart cities can synergistically enhance UCR. Based on the social-ecological-technological systems (SETS) perspective, this paper employs the staggered DID models to examine the policy synergetic effects of DPP on UCR. Results show that DPP increases UCR by an average of 5.43%. DPP establishes comprehensive adaptation mechanisms, including expanding green spaces, developing digital infrastructure, and promoting green technological innovation. The policy effect is more pronounced in inland cities, small cities, and cities with lower climate risks. While boosting the local UCR, DPP also improves the average UCR by 27.00% in neighboring areas. Our research highlights the synergistic governance between ecological and technological systems. It provides empirical evidence for climate adaptation through green and smart transformations in rapidly urbanizing regions.

气候风险威胁着城市经济、社会和生态系统的可持续发展。城市气候适应能力（UCR）难以通过单一政策全面提升。森林城市和智慧城市是基于自然和技术驱动的解决方案的典型例子，它们对环境的影响得到了广泛的研究。然而，森林城市和智慧城市的双重试点政策（DPP）是否能协同提高UCR仍不确定。基于社会-生态-技术系统（set）视角，采用交错DID模型考察了DPP对UCR的政策协同效应。结果表明，DPP使UCR平均提高5.43%。DPP建立了包括扩大绿色空间、发展数字基础设施、推动绿色技术创新在内的综合适应机制。政策效应在内陆城市、小城市和气候风险较低的城市更为明显。在提高当地UCR的同时，DPP还使周边地区的平均UCR提高了27.00%。我们的研究强调生态系统和技术系统之间的协同治理。它为快速城市化地区通过绿色和智能转型适应气候变化提供了经验证据。

{"title":"Toward greener, smarter, and more resilient cities: Assessing the impact of dual pilot policies of forest city and smart city on urban climate resilience in China","authors":"Yaobin Liu , Sheng Hu , Shuoshuo Li , Weifeng Deng","doi":"10.1016/j.scs.2026.107155","DOIUrl":"10.1016/j.scs.2026.107155","url":null,"abstract":"<div><div>Climate risks threaten the sustainable development of urban economies, societies, and ecosystems. Urban climate resilience (UCR) is difficult to comprehensively improve through single policies. Forest cities and smart cities are typical examples of nature-based and technology-driven solutions, which have been extensively studied for their environmental impacts. However, it remains uncertain whether dual pilot policies (DPP) for forest cities and smart cities can synergistically enhance UCR. Based on the social-ecological-technological systems (SETS) perspective, this paper employs the staggered DID models to examine the policy synergetic effects of DPP on UCR. Results show that DPP increases UCR by an average of 5.43%. DPP establishes comprehensive adaptation mechanisms, including expanding green spaces, developing digital infrastructure, and promoting green technological innovation. The policy effect is more pronounced in inland cities, small cities, and cities with lower climate risks. While boosting the local UCR, DPP also improves the average UCR by 27.00% in neighboring areas. Our research highlights the synergistic governance between ecological and technological systems. It provides empirical evidence for climate adaptation through green and smart transformations in rapidly urbanizing regions.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107155"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Urban blue-green spaces for wintertime microclimate regulation: Interactive and marginal effects 冬季微气候调节的城市蓝绿空间：交互效应和边际效应

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2025-12-26 DOI: 10.1016/j.scs.2025.107095

Wei Ding , Mengyang Liu , Yunni Wu , Wei Feng , Hong Chen

Urban blue-green space planning is a critical strategy for mitigating urban heat islands and air pollution. However, the mechanisms of their climatic regulation and interactive effects remain insufficiently understood, particularly under wintertime conditions when atmospheric stability and pollution accumulation are most pronounced. Using the six green wedges of Wuhan as a case, this study employed the WRF-chem model coupled with an urban canopy scheme, validated against national monitoring data, to simulate multiple winter scenarios and examine the regulatory role of blue-green spaces at the urban-rural fringe. Results show that: (1) both blue and green spaces within the wedges exert significant effects on 2 m air temperature, though their impacts are largely independent; (2) while the direct microclimatic effects of green spaces are limited, they synergise with blue spaces to enhance urban ventilation and facilitate PM_2.5 dispersion; and (3) blue spaces define the spatial extent of temperature regulation, whereas green spaces moderate diurnal temperature variations. Together, blue-green spaces constrained thermal differences within a 2.05 km buffer to <0.1 °C. In the green-only scenario, the maximum ventilation length (Lmax) decreased by 0.68 km; in the absence of both, Lmax decreased by 0.75 km; in the blue-only scenario, the maximum daytime temperature difference (Dmax) increased by 0.23 °C. These findings highlight that rational configuration of blue and green spaces, considering their diurnal variability and seasonal performance in winter, can generate synergistic benefits for urban ventilation and particulate dispersion. This study provides practical insights for blue-green infrastructure design and spatial planning strategies aimed at improving wintertime climate resilience in rapidly urbanising regions.

城市蓝绿空间规划是缓解城市热岛和空气污染的重要策略。然而，它们的气候调节和相互作用的机制仍然没有得到充分的了解，特别是在大气稳定性和污染积累最明显的冬季条件下。本研究以武汉市6个绿楔为例，采用WRF-chem模型和城市冠层方案，通过国家监测数据验证，模拟了多个冬季情景，并考察了城乡边缘蓝绿空间的调节作用。结果表明：(1)楔形区域内的蓝色和绿色空间对2 m气温均有显著影响，但二者的影响在很大程度上是相互独立的；(2)绿地的直接小气候效应有限，但可与蓝色空间协同作用，增强城市通风，促进PM2.5扩散；(3)蓝色空间定义了温度调节的空间范围，而绿色空间则调节了温度的日变化。总之，蓝绿空间将2.05公里缓冲区内的温差限制在0.1°C以内。在纯绿色场景下，最大通风长度（Lmax）减少了0.68 km；两者均不存在时，Lmax减小0.75 km；在纯蓝色场景下，最大日间温差（Dmax）增加了0.23℃。这些发现强调，考虑到蓝色和绿色空间的日变化和冬季的季节性表现，合理配置它们可以产生协同效益，促进城市通风和颗粒物扩散。该研究为蓝绿基础设施设计和空间规划策略提供了实用见解，旨在提高快速城市化地区冬季气候适应能力。

{"title":"Urban blue-green spaces for wintertime microclimate regulation: Interactive and marginal effects","authors":"Wei Ding , Mengyang Liu , Yunni Wu , Wei Feng , Hong Chen","doi":"10.1016/j.scs.2025.107095","DOIUrl":"10.1016/j.scs.2025.107095","url":null,"abstract":"<div><div>Urban blue-green space planning is a critical strategy for mitigating urban heat islands and air pollution. However, the mechanisms of their climatic regulation and interactive effects remain insufficiently understood, particularly under wintertime conditions when atmospheric stability and pollution accumulation are most pronounced. Using the six green wedges of Wuhan as a case, this study employed the WRF-chem model coupled with an urban canopy scheme, validated against national monitoring data, to simulate multiple winter scenarios and examine the regulatory role of blue-green spaces at the urban-rural fringe. Results show that: (1) both blue and green spaces within the wedges exert significant effects on 2 m air temperature, though their impacts are largely independent; (2) while the direct microclimatic effects of green spaces are limited, they synergise with blue spaces to enhance urban ventilation and facilitate PM<sub>2.5</sub> dispersion; and (3) blue spaces define the spatial extent of temperature regulation, whereas green spaces moderate diurnal temperature variations. Together, blue-green spaces constrained thermal differences within a 2.05 km buffer to <0.1 °C. In the green-only scenario, the maximum ventilation length (Lmax) decreased by 0.68 km; in the absence of both, Lmax decreased by 0.75 km; in the blue-only scenario, the maximum daytime temperature difference (Dmax) increased by 0.23 °C. These findings highlight that rational configuration of blue and green spaces, considering their diurnal variability and seasonal performance in winter, can generate synergistic benefits for urban ventilation and particulate dispersion. This study provides practical insights for blue-green infrastructure design and spatial planning strategies aimed at improving wintertime climate resilience in rapidly urbanising regions.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107095"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-resolution spatiotemporal dynamic simulation and driving force analysis of carbon emissions in coastal cities: The case of Ningbo City 沿海城市碳排放高分辨率时空动态模拟及驱动力分析——以宁波市为例

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-01-30 DOI: 10.1016/j.scs.2026.107195

Guangxin Cui , Xusheng Cheng , Yanwei Sun , Chao Gao , Zheng Duan , Tian Ruan

Coastal port cities are key regions for carbon emissions (CEs) research in China, due to their industrial density, frequent transportation, and diverse human activities. Taking Ningbo City as a case study, this study employed a top-down accounting method and integrated multiple sources of geospatial data to reveal the spatiotemporal distribution characteristics of CEs from four sectors, including industrial, residential, logistical, and commercial, from 2013 to 2022. Monte Carlo simulation was further applied to assess uncertainty. The driving factors were analyzed using the Logarithmic Mean Divisia Index (LMDI) decomposition model. The findings show that the total CEs in Ningbo City increased steadily, with the spatial pattern evolving from early single-core aggregation to coastal multi-center expansion. The industrial sector is the primary source, with emissions concentrated in ports and coastal industrial zones. Residential and commercial emissions exhibit a multi-point distribution and low-value expansion pattern, while logistical emissions have remained relatively stable and are primarily concentrated in the urban area. Economic development is the core driver of CEs growth, while energy intensity and carbon emission factors have had an inhibitory effect. This study provides a theoretical basis and practical support for high-resolution urban CEs monitoring and low-carbon policy formulation in coastal cities.

沿海港口城市具有工业密度大、交通运输频繁、人类活动多样等特点，是中国碳排放研究的重点区域。本文以宁波市为例，采用自顶向下的核算方法，整合多源地理空间数据，揭示了2013 - 2022年宁波市工业、住宅、物流、商业4个行业消费成本的时空分布特征。蒙特卡罗模拟进一步评估了不确定性。采用对数平均分差指数（LMDI）分解模型对驱动因素进行分析。结果表明：宁波市总体消费空间呈稳定增长趋势，空间格局由早期的单中心集聚向沿海多中心扩张演变；工业部门是主要来源，排放集中在港口和沿海工业区。住宅和商业排放呈现多点分布和低值扩张格局，而物流排放保持相对稳定，主要集中在城市地区。经济发展是能源消费增长的核心驱动力，能源强度和碳排放因素对能源消费增长具有抑制作用。本研究为沿海城市高分辨率碳排放监测和低碳政策制定提供了理论依据和实践支持。

{"title":"High-resolution spatiotemporal dynamic simulation and driving force analysis of carbon emissions in coastal cities: The case of Ningbo City","authors":"Guangxin Cui , Xusheng Cheng , Yanwei Sun , Chao Gao , Zheng Duan , Tian Ruan","doi":"10.1016/j.scs.2026.107195","DOIUrl":"10.1016/j.scs.2026.107195","url":null,"abstract":"<div><div>Coastal port cities are key regions for carbon emissions (CEs) research in China, due to their industrial density, frequent transportation, and diverse human activities. Taking Ningbo City as a case study, this study employed a top-down accounting method and integrated multiple sources of geospatial data to reveal the spatiotemporal distribution characteristics of CEs from four sectors, including industrial, residential, logistical, and commercial, from 2013 to 2022. Monte Carlo simulation was further applied to assess uncertainty. The driving factors were analyzed using the Logarithmic Mean Divisia Index (LMDI) decomposition model. The findings show that the total CEs in Ningbo City increased steadily, with the spatial pattern evolving from early single-core aggregation to coastal multi-center expansion. The industrial sector is the primary source, with emissions concentrated in ports and coastal industrial zones. Residential and commercial emissions exhibit a multi-point distribution and low-value expansion pattern, while logistical emissions have remained relatively stable and are primarily concentrated in the urban area. Economic development is the core driver of CEs growth, while energy intensity and carbon emission factors have had an inhibitory effect. This study provides a theoretical basis and practical support for high-resolution urban CEs monitoring and low-carbon policy formulation in coastal cities.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107195"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Augmenting urban planning with computer vision: A review of the state-of-the-art 用计算机视觉增强城市规划：最新进展综述

IF 12 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Sustainable Cities and Society

Pub Date : 2026-03-01 Epub Date: 2026-02-04 DOI: 10.1016/j.scs.2026.107209

Raveena Marasinghe , Tan Yigitcanlar , Xinyu Fu , Steven Jige Quan

Computer Vision (CV) offers powerful methods for analysing built environments, yet its integration into planning workflows remains fragmented. This study conducts a systematic review of CV applications in urban planning using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol, synthesising prevailing models, methods, and application domains. The review identifies five dominant CV research clusters in urban contexts (built environment analysis, urban sensing and data acquisition, smart mobility, methodological advances, and 3D urban modelling) and synthesises that CV is primarily used to extract physical and perceptual urban features, support diagnostic analytics, and enable emerging visualisation and generative design workflows. Advances in deep learning, convolutional neural networks, and emerging foundation models (including vision transformers and diffusion-based generative systems) are expanding capability across diverse CV tasks and lowering barriers to adoption. Building on an inductive synthesis of application patterns across the reviewed studies, the paper proposes an Urban Visual Intelligence (UVI) hierarchy that clarifies how imagery is translated into progressively more planning-relevant outputs, from observation and diagnosis to associative explanation, forecasting, and intervention prototyping. The review also highlights constraints related to data representativeness, transferability, interpretability, privacy and generative unreliability, underscoring the need for stronger validation and governance as outputs become more decision relevant. Overall, the review consolidates how CV is reshaping urban analytics and offers a structured basis for responsible integration into planning practice.

计算机视觉（CV）为分析建筑环境提供了强大的方法，然而它与规划工作流程的集成仍然是碎片化的。本研究使用系统评价和荟萃分析（PRISMA）协议的首选报告项目对CV在城市规划中的应用进行了系统回顾，综合了流行的模型、方法和应用领域。该综述确定了城市背景下五个主要的CV研究集群（建筑环境分析，城市传感和数据采集，智能移动，方法进步和3D城市建模），并综合了CV主要用于提取物理和感知城市特征，支持诊断分析，并使新兴的可视化和生成设计工作流程成为可能。深度学习、卷积神经网络和新兴基础模型（包括视觉转换器和基于扩散的生成系统）的进步正在扩展不同CV任务的能力，并降低采用障碍。基于对所回顾研究的应用模式的归纳综合，本文提出了一个城市视觉智能（UVI）层次结构，该层次结构阐明了如何将图像逐步转化为与规划相关的输出，从观察和诊断到关联解释、预测和干预原型。审查还强调了与数据代表性、可转移性、可解释性、隐私性和生成不可靠性有关的制约因素，强调了随着产出越来越与决策相关，需要加强验证和治理。总体而言，该综述巩固了CV如何重塑城市分析，并为负责任的规划实践整合提供了结构化的基础。

{"title":"Augmenting urban planning with computer vision: A review of the state-of-the-art","authors":"Raveena Marasinghe , Tan Yigitcanlar , Xinyu Fu , Steven Jige Quan","doi":"10.1016/j.scs.2026.107209","DOIUrl":"10.1016/j.scs.2026.107209","url":null,"abstract":"<div><div>Computer Vision (CV) offers powerful methods for analysing built environments, yet its integration into planning workflows remains fragmented. This study conducts a systematic review of CV applications in urban planning using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol, synthesising prevailing models, methods, and application domains. The review identifies five dominant CV research clusters in urban contexts (built environment analysis, urban sensing and data acquisition, smart mobility, methodological advances, and 3D urban modelling) and synthesises that CV is primarily used to extract physical and perceptual urban features, support diagnostic analytics, and enable emerging visualisation and generative design workflows. Advances in deep learning, convolutional neural networks, and emerging foundation models (including vision transformers and diffusion-based generative systems) are expanding capability across diverse CV tasks and lowering barriers to adoption. Building on an inductive synthesis of application patterns across the reviewed studies, the paper proposes an Urban Visual Intelligence (UVI) hierarchy that clarifies how imagery is translated into progressively more planning-relevant outputs, from observation and diagnosis to associative explanation, forecasting, and intervention prototyping. The review also highlights constraints related to data representativeness, transferability, interpretability, privacy and generative unreliability, underscoring the need for stronger validation and governance as outputs become more decision relevant. Overall, the review consolidates how CV is reshaping urban analytics and offers a structured basis for responsible integration into planning practice.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"138 ","pages":"Article 107209"},"PeriodicalIF":12.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147399438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0