Sustainable Cities and Society最新文献

{"title":"Exploring the effects of street canyon morphology on LST within different street types using causal inference and machine learning","authors":"Ziyi Liu ,&nbsp;Hong Yuan ,&nbsp;Jianing Luo","doi":"10.1016/j.scs.2025.106814","DOIUrl":"10.1016/j.scs.2025.106814","url":null,"abstract":"<div><div>There is currently a lack of classification methods for street canyon morphology at the street-scale level. This can impede the development of targeted cooling strategies tailored to the specific characteristics of different street morphologies. This study quantifies street canyon morphology using street-view hemisphere images and compares multiple clustering models to identify the optimal model and parameters. Subsequently, machine learning is coupled with causal inference models to explore the associative mechanisms between different street canyon morphology indices and multi-time land surface temperature (LST). The results reveal that spectral clustering divides streets into three categories of wide streets and two categories of narrower alleys. Different street types exhibit distinct correlation trends with LST, highlighting the importance of clustering algorithms. In conjunction with the results of causal inference, it is observed that alleys with high canopy coverage and broad streets equipped with road-center hedges demonstrate superior cooling capabilities, with cooling effects of 23.56 % and 18.81 %, respectively. Conversely, for broad streets with lower levels of greening, increasing the height of roadside buildings can be an effective strategy to maximize the utilization of building shadows and wind for cooling purposes. This study emphasizes vegetation as a key factor in altering street canyon morphology to achieve cooling effects, particularly in stock developments.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106814"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107721","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}

{"title":"What if transformers revolutionize geospatial forecasting? ConvLSTM-Transformer-ARIMA framework for LST forecasting","authors":"He Zhang,&nbsp;Rui Liu,&nbsp;Zeren Dawa,&nbsp;Runcan Han,&nbsp;Qi Zhou","doi":"10.1016/j.scs.2025.106794","DOIUrl":"10.1016/j.scs.2025.106794","url":null,"abstract":"<div><div>The present study introduces a novel integrated framework that merges Convolutional Long Short-Term Memory (ConvLSTM) networks, Transformer architecture, and Autoregressive Integrated Moving Average (ARIMA) models to predict the dynamics of Land Surface Temperature (LST) in China’s Sichuan-Chongqing region. The region’s complex topography and rapid urbanization present substantial difficulties for accurate LST forecasting. To tackle these challenges, we employed comprehensive LST raster data from 2001 to 2020, coupled with 19 influencing factors. Extensive collinearity and redundancy analyses were conducted to identify 11 critical drivers, such as Carbon Fixation Potential (CFP), Thermal Circulation Potential (TCP), Net Primary Production (NPP), Artificial Light Heat Index (ALHI), and factors related to urban expansion. The hybrid model capitalizes on the strengths of ConvLSTM in capturing spatiotemporal dependencies, Transformer in enhancing global context modeling, and ARIMA in short-term trend forecasting. Compared to conventional CNN and LSTM models, the proposed framework achieves an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.9054, representing an approximately 10% improvement in explained variance, while maintaining comparable MAE levels. This indicates that the hybrid architecture enhances the ability to capture complex spatiotemporal dynamics and improves the stability of predictions. Meanwhile, the model’s predictive accuracy was verified using observed LST data from 2021 to 2023, showing high precision with low Mean Absolute Error (MAE) and Mean Squared Error (MSE), as well as high Pearson Correlation Coefficient (PCC) and Coefficient of Determination (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>). Moreover, SHAP (SHapley Additive exPlanations) analysis pinpointed key factors influencing LST variations, with vegetation productivity (GPP, NPP) and meteorological parameters (WDSP, STP) emerging as dominant contributors. This research underscores the efficacy of the hybrid ConvLSTM-Transformer-ARIMA model in capturing complex spatiotemporal LST dynamics and offers actionable insights for urban planning and climate adaptation strategies in regions with challenging environmental conditions.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106794"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107722","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}

{"title":"Compound urban heat risk revealed by co-location of social vulnerability and elevated temperatures in London, UK: A spatial analysis","authors":"Emma Roberts,&nbsp;Ting Sun,&nbsp;Mark Pelling","doi":"10.1016/j.scs.2025.106756","DOIUrl":"10.1016/j.scs.2025.106756","url":null,"abstract":"<div><div>Heatwaves are worsening globally under climate change, with significant impacts on human health. Cities are at increased risk due to the urban heat island effect, and vulnerable populations are more likely to experience morbidity and mortality from extreme heat. Improved modelling of social vulnerability is needed in urban areas to better plan for worsening heatwaves and their public health impacts. This study performs Principal Component Analysis (PCA) on fifteen heat-health vulnerability indicators for the borough of Hackney in London, UK and develops a Heat Vulnerability Index (HVI) to rank relative social vulnerability within the borough. Air temperature during the peak of the 2022 UK heatwave is then modelled for the study area to represent the hazard of extreme heat. Social vulnerability to extreme heat is found to vary spatially within Hackney and there are clusters of statistically significant high and low vulnerability scores present. Areas scoring highly on the HVI were significantly associated with higher temperatures during the 2022 UK heatwave, highlighting a positive association between social vulnerability and the hazard intensity of extreme heat. This heat vulnerability map can be used by urban planners and emergency managers to target heat-health interventions to those most at-risk during a heatwave.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106756"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061080","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}

{"title":"Unveiling pandemic-driven mobility shifts: A S-GTWR analysis of bike-sharing and taxi systems in Washington, D.C","authors":"Jianmin Jia ,&nbsp;Shiyu He ,&nbsp;Hui Zhang ,&nbsp;Yan Xiao","doi":"10.1016/j.scs.2025.106802","DOIUrl":"10.1016/j.scs.2025.106802","url":null,"abstract":"<div><div>A comprehensive analysis of urban transportation systems is essential for effective planning and management. As a representative combination of public and private mobility services, bike-sharing and taxi systems have undergone dynamic changes, particularly during public health crises. This study employs a semi-parametric Geographically and Temporally Weighted Regression (S-GTWR) model to quantitatively evaluate the impacts of socio-demographic, land use, traffic service, and weather-related factors on bike-sharing and taxi ridership in Washington, D.C., throughout the COVID-19 pandemic and subsequent recovery stages. Utilizing census block group-level data, the findings reveal that bike-sharing usage rebounded to near pre-pandemic levels by 2021–2022, whereas taxi ridership remained at approximately 30 % of its pre-pandemic volume. This disparity highlights significant shifts in mobility behavior. Among several models tested, including OLS, GWR, TWR, and GTWR, the S-GTWR model demonstrated superior performance and was selected for spatiotemporal pattern analysis. The model effectively captured dynamic changes in influencing factors by differentiating between trip origins and destinations, thereby offering valuable insights for policymaking. Notably, the variable representing households without vehicles (AUO) was negatively associated with pre-pandemic trip volume, suggesting a behavioral shift during the pandemic from public transit toward alternative modes like bike-sharing and taxis. These results underscore the importance of targeted mobility strategies in response to evolving travel behaviors. The findings provide actionable insights for urban planners and transportation operators to optimize mobility services and enhance urban resilience during public health crises.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106802"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050295","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}

{"title":"Assessing urban emergency medical services accessibility for older adults considering ambulance trafficability using a deep learning approach","authors":"Zhuo Liu ,&nbsp;Enjia Zhang ,&nbsp;Shuo Pan ,&nbsp;Sichun Li ,&nbsp;Ying Long ,&nbsp;Frank Witlox","doi":"10.1016/j.scs.2025.106804","DOIUrl":"10.1016/j.scs.2025.106804","url":null,"abstract":"<div><div>Rapid urbanization and population aging have made equitable Emergency Medical Services (EMS) access for older adults a critical challenge in high-density cities. This study develops a deep learning framework to evaluate EMS accessibility, considering ambulance trafficability derived from street view images (SVIs). A Multi-Scale Vision Transformer (MSViT) model classifies SVIs into impassable, narrow, and passable categories to assess road conditions. Travel speeds are then assigned based on the classified trafficability and road hierarchy data. The framework measures the pre-hospital time through two-stage travel (emergency center-to-patient and patient-to-hospital), while evaluating accessibility through two complementary metrics: the inverse of the shortest total pre-hospital time, and a composite accessibility score with Gaussian time-decay weighting for all facilities within 15-minute service ranges. A case study in Beijing’s Old City demonstrated that considering ambulance trafficability reduces the estimated 15-minute coverage from 94.18 % to 83.14 %, revealing significant overestimation when road conditions are neglected. Spatially, peripheral areas achieved better nearest-facility response times, whereas central regions dominated in comprehensive service coverage. Additionally, EMS accessibility patterns strongly correlated with older adults’ distribution, showing limited income-based disparities. This study shifts the focus from supply-demand balancing to road system management in EMS accessibility, which can be integrated with existing methods to support more sustainable and targeted infrastructure optimization in aging cities.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106804"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050299","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}

{"title":"Let’s make PED work - How current knowledge can contribute to future positive energy districts","authors":"Jelena Nikolic,&nbsp;Jakob Zinck Thellufsen,&nbsp;Peter Sorknæs,&nbsp;Poul Thøis Madsen,&nbsp;Lasse Schytt Nørgaard","doi":"10.1016/j.scs.2025.106817","DOIUrl":"10.1016/j.scs.2025.106817","url":null,"abstract":"<div><div>The concept of Positive Energy Districts (PEDs) i.e. urban units that produce surplus energy, has been recognized as a possible enabler of energy change. In literature, PEDs are defined in three main ways: virtual, dynamic, and autonomous, each offering different system boundaries for energy production. This paper examines these definitions while varying the inclusion of energy sectors (industry, transportation, buildings), enabling an assessment of PEDs as a tool to quantify the impact of district size and sectoral coverage. The general methodology presented in the study has been applied to district of Aalborg East in Denmark, to demonstrate its practical utility. Results indicate that system complexity significantly affects PED feasibility, influenced by local conditions such as weather and land availability. The choice of PED definition determines which energy sectors can be feasibly included. In this case, when energy-intensive sectors like industry and transportation are considered, the most feasible PED is achieved through the virtual approach. Compared to PEDs in which energy is strictly produced within the system boundaries, the annual costs of the PED virtual are 6 % lower than those of the PED dynamic model. Furthermore, even when the PED includes only households, the amount of energy produced but not utilized within the PED in the virtual model is 77 % lower compared to the autonomous model, and 20 % lower compared to the dynamic model.</div><div>Finally, the study highlights the importance of tailoring PED strategies to local contexts and integrating them into broader urban energy networks. This ensures electricity exchange between districts, supports national decarbonization goals, and promotes social inclusion and climate neutrality.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106817"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107167","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}

{"title":"Divergent carbon emission mitigation pathways toward sustainable development: Heterogeneous effects of the digital economy in urban centers versus boundary regions","authors":"Langang Feng ,&nbsp;Jiaxing Lu ,&nbsp;Jin Hu ,&nbsp;Muhammad Irfan ,&nbsp;Kaiya Wu","doi":"10.1016/j.scs.2025.106808","DOIUrl":"10.1016/j.scs.2025.106808","url":null,"abstract":"<div><div>Significant disparities in economic structure and environmental governance between urban centers and boundary areas underscore the need to explore spatially differentiated carbon reduction (CR) mechanisms enabled by the digital economy (DE). Leveraging panel data from 279 Chinese cities (2011–2022), this study employs machine learning models, SHapley Additive exPlanations (SHAP), and econometric analysis to dissect the heterogeneous CR effects of DE subsystems across urban functional zones. Results reveal a pronounced “central effect”, where DE-driven carbon mitigation is substantially stronger in urban centers than in boundary areas. Key drivers include telecommunications development (TDI) and digital finance (DFI), contributing 0.76 and -0.19 to central effect of CR, respectively, while internet penetration (IPI) and digital talent (DTI) exhibit limited impacts. Notably, resource-based cities and regions at lower administrative tiers benefit disproportionately from DE’s CR potential, whereas high-innovation cities show diminished spatial disparities due to balanced digital adoption. These findings challenge the homogeneous treatment of DE in existing literature and provide actionable insights for policymakers and corporate strategists to design spatially targeted green policies. By aligning digital infrastructure investments with regional industrial characteristics and prioritizing DFI-TDI synergies, cities can amplify DE’s role in achieving climate goals while addressing core-periphery inequities.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106808"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107163","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}

{"title":"Enhancing neighborhood-scale building performance simulation through building classification and automated data acquisition: Supporting the Dutch heating transition","authors":"Chaobo Zhang,&nbsp;Pieter-Jan Hoes,&nbsp;Bowen Tian,&nbsp;Ruqian Zhang,&nbsp;Roel Loonen","doi":"10.1016/j.scs.2025.106811","DOIUrl":"10.1016/j.scs.2025.106811","url":null,"abstract":"<div><div>Neighborhood-scale building performance simulation is essential for advancing the sustainable heating transition in the Netherlands. Such simulations require significant computing resources and are often hindered by a lack of access to detailed building information. This paper proposes a neighborhood-scale building performance simulation method enhanced with building classification and automated data acquisition to overcome these challenges. Deep learning-based models are developed to identify windows, doors, and photovoltaic (PV) panels from street view and satellite images. They enable the acquisition of critical modeling information that might be not readily accessible, including window/door area fractions, PV panel locations, and zoning configurations. Bayesian optimization is applied for model calibration to determine suitable values for uncertain building information (i.e., infiltration rates). Additionally, a clustering-based building classification approach is proposed to extract representative buildings from all the buildings in a neighborhood. Similar buildings usually have comparable heating performance, making it feasible to use a few representative buildings to simulate a large number of buildings. The proposed building performance simulation method is evaluated using the 1452 terraced houses located in a Dutch neighborhood. The identification accuracy of deep learning is 98.9 % for windows/doors and 98.6 % for PV panels. A total of 123 representative houses are extracted and modeled, leading to a 91.5 % reduction in simulation time. The representative house models exhibit a very small absolute percentage error (0.17 %) in simulating the neighborhood's annual gas consumption after model calibration.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106811"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107714","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}

{"title":"Corrigendum to “A novel indicator for assessing spatial coupling relationships within hybrid landscapes comprising diverse land cover types and its application to explaining urban thermal environment” [Sustainable Cities and Society 130 (2025) 106595]","authors":"Tao Mu ,&nbsp;Ruting Zhao ,&nbsp;Huawei Li ,&nbsp;Yakai Lei ,&nbsp;Qiuyuan Chen ,&nbsp;Guohang Tian ,&nbsp;Yali Zhang ,&nbsp;Bo Mu","doi":"10.1016/j.scs.2025.106828","DOIUrl":"10.1016/j.scs.2025.106828","url":null,"abstract":"","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106828"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267453","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}

{"title":"Transforming underutilized urban spaces into green infrastructure in Global South cities: A systematic review","authors":"Amal Saleh Mohammed Al hothaufi ,&nbsp;Yike Hu ,&nbsp;Akram Ahmed Noman Alabsi ,&nbsp;Nour El Houda Ben Ameur ,&nbsp;Ghada A. Alssadah ,&nbsp;Haitham A. Ashah","doi":"10.1016/j.scs.2025.106816","DOIUrl":"10.1016/j.scs.2025.106816","url":null,"abstract":"<div><div>Rapid urbanization in cities of the Global South has exacerbated environmental degradation and escalated pressure on land resources, leading to intricate challenges regarding sustainability, liveability, and equity. Repurposing underutilized land into multifunctional green infrastructure (GI) is urgent. This systematic review synthesizes findings from 30 peer-reviewed studies published between 2014 and 2025, following the PRISMA protocol, to evaluate planning frameworks and methodological approaches for such transformations. The reviewed literature, covering case studies in Africa, Asia, and Latin America, primarily focuses on brownfields, vacant lots, and underused public spaces. Analysis reveals four thematic clusters: (1) spatial analysis and site identification, (2) participatory and community-led planning, (3) governance and policy mechanisms, and (4) multifunctionality in GI strategies. Key gaps include the absence of a unified definition of “underutilized” spaces, reliance on static spatial datasets that overlook informal land use and changing vacancy patterns, and limited integration of justice dimensions specifically social, spatial, and procedural justice into GI planning. To address these gaps, the review recommends: (a) creating standardized classification systems that incorporate land tenure, contamination status, and historical use to counter definitional inconsistencies; (b) using hybrid geospatial data that integrate the temporal, spectral, and morphological dimensions data to overcome limitations of static datasets; and (c) prioritizing GI interventions in marginalized and high-risk communities to embed justice considerations. Finally, to overcome weak governance frameworks, inclusive models should be institutionalized to support co-design, prevent displacement, and strengthen resilience. These recommendations underscore the need for justice-oriented, context-specific GI strategies that reflect the socio-spatial and ecological complexities of Global South cities.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"132 ","pages":"Article 106816"},"PeriodicalIF":12.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107715","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}