Computers Environment and Urban Systems最新文献

Renewable energy adoption in urban residential communities in China: An agent-based model for assessing intervention impact 中国城市居民社区采用可再生能源：基于主体的干预影响评估模型

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-19 DOI: 10.1016/j.compenvurbsys.2025.102323

Hua Du , Qi Han , Bauke de Vries , Jun Sun

{"title":"Renewable energy adoption in urban residential communities in China: An agent-based model for assessing intervention impact","authors":"Hua Du , Qi Han , Bauke de Vries , Jun Sun","doi":"10.1016/j.compenvurbsys.2025.102323","DOIUrl":"10.1016/j.compenvurbsys.2025.102323","url":null,"abstract":"<div><div>Designing effective policy interventions is an essential instrument to promote the widespread adoption of photovoltaic (PV) systems in the residential sector. Designing such policies and evaluating their effectiveness requires an approach that allows for simulation in the complex system setting of the built environment. In this study we applied Agent-Based Modelling to evaluate the effectiveness of two policies (i.e., information campaign and demonstration projects) and two community factors (i.e., community size and required agreement rate) to promote the adoption of residential community PV diffusion in Chinese cities. This model is developed based on the empirical results of a previous discrete choice experiment. The results show that lowering the required agreement rate for community decisions contributes to an increase in PV adoption, while community size has little impact on adoption diffusion. We found that combining the two policy interventions or combining them with a community factor (i.e., lowering the required agreement rate) can effectively promote the adoption of community PV. Policy intervention implications and suggestions are presented.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102323"},"PeriodicalIF":7.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144312561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Measuring nuanced walkability: Leveraging ChatGPT's vision reasoning with multisource spatial data 测量细微差别的步行性：利用ChatGPT的视觉推理与多源空间数据

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-18 DOI: 10.1016/j.compenvurbsys.2025.102319

Donghwan Ki , Hojun Lee , Keundeok Park , Jaehyun Ha , Sugie Lee

{"title":"Measuring nuanced walkability: Leveraging ChatGPT's vision reasoning with multisource spatial data","authors":"Donghwan Ki , Hojun Lee , Keundeok Park , Jaehyun Ha , Sugie Lee","doi":"10.1016/j.compenvurbsys.2025.102319","DOIUrl":"10.1016/j.compenvurbsys.2025.102319","url":null,"abstract":"<div><div>Recent advances in urban analytical tools, particularly street view image (SVI) data and computer vision (CV) algorithms, such as semantic segmentation, have enhanced walkability measurement by enabling the automated assessment of mesoscale features, such as greenery proportions. However, while SVI data contain rich environmental information, off-the-shelf CV models generally struggle to capture microscale features—design details attached to mesoscale elements, such as the quality of greenery or sidewalk maintenance. Moreover, because CV algorithms typically evaluate environmental features in isolation, they often fail to account for spatial arrangements and visual harmony among features, limiting their ability to support a holistic assessment of walkability. Recently, multimodal large language models (MLLMs), particularly ChatGPT, have introduced a transformative approach to image analysis by mimicking human perception. This study proposes a comprehensive walkability measurement framework that leverages ChatGPT's vision reasoning across multiple spatial data, including SVIs and GIS land use and road network maps. To validate this framework, we compare ChatGPT-generated walkability ratings with human assessments and examine their relationship with reported walking behavior data. Furthermore, by comparing ChatGPT-generated outcomes with evaluations from conventional walkability measurement tools, such as GIS and off-the-shelf CV models, we highlight the novel contribution of ChatGPT in walkability assessment. This research advances the literature by introducing a ChatGPT-based framework for a more comprehensive walkability assessment.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102319"},"PeriodicalIF":7.1,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Architecting urban epidemic defense: A hierarchical region-individual control framework for optimizing large-scale individual mobility interventions 构建城市流行病防御：优化大规模个人流动干预的分层区域-个人控制框架

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-14 DOI: 10.1016/j.compenvurbsys.2025.102312

Yuxiao Luo , Ling Yin , Kemin Zhu , Kang Liu

{"title":"Architecting urban epidemic defense: A hierarchical region-individual control framework for optimizing large-scale individual mobility interventions","authors":"Yuxiao Luo , Ling Yin , Kemin Zhu , Kang Liu","doi":"10.1016/j.compenvurbsys.2025.102312","DOIUrl":"10.1016/j.compenvurbsys.2025.102312","url":null,"abstract":"<div><div>In urban areas, high population density and extensive mobility can foster rapid transmission of emerging infectious diseases, particularly acute respiratory infections, which could lead to significant public health challenges and widespread social impact. EPidemic Control (EPC) strategies like mobility interventions tailored for each individual effectively mitigate these risks, balancing the safeguarding of public health with the socio-economic impacts. However, a large number of urban residents (e.g., millions) with complex spatiotemporal activities in modern cities pose a large-scale challenge of optimizing mobility interventions at an individual-level. To address this issue, this study introduces a framework of Hierarchical Region-Individual Control for Epidemic (Hi-RICE) to dynamically adapt specific interventions to large-scale individuals in complex urban epidemic scenarios with given control objectives. Hi-RICE initially assesses the dynamic infectious risk and contact risk for each individual according to their spatiotemporal behaviors. Subsequently, regional control agents, utilizing multi-agent reinforcement learning, optimize the appropriate intervention intensity for each region. Finally, specific mobility interventions are applied to high-risk individuals in each region according to their optimized control intensities. Utilizing Shenzhen, China, as a case of a megacity, simulations validate the proposed framework’s effectiveness and adaptability across various epidemic conditions, demonstrating its capacity to optimally balance epidemic control and socio-economic sustainability.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102312"},"PeriodicalIF":7.1,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing urban green space spatial patterns for thermal environment improvement: A multi-objective approach in the context of urban renewal 基于热环境改善的城市绿地空间格局优化：城市更新背景下的多目标方法

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-12 DOI: 10.1016/j.compenvurbsys.2025.102320

Liangguo Lin , Yaolong Zhao , Juchao Zhao

{"title":"Optimizing urban green space spatial patterns for thermal environment improvement: A multi-objective approach in the context of urban renewal","authors":"Liangguo Lin , Yaolong Zhao , Juchao Zhao","doi":"10.1016/j.compenvurbsys.2025.102320","DOIUrl":"10.1016/j.compenvurbsys.2025.102320","url":null,"abstract":"<div><div>The rapid and inevitable trend of urbanization has amplified urban thermal challenges, intensifying the urban heat island (UHI) effect. Given the constraints of limited urban land resources, optimizing the spatial patterns of urban green space (UGS) to maximize their cooling potential is essential for mitigating urban thermal environments and supporting effective urban renewal planning. This research integrates the XGBoost model with the NSGA-II algorithm to propose a multi-objective approach to optimize UGS spatial patterns for thermal environment improvement, using the central urban area of Guangzhou, China, as a case study in the context of urban renewal. To further assess the effectiveness of optimization, the Shapley additive explanation (SHAP) model was employed to examine how landscape pattern metrics, which characterize UGS spatial patterns, influence LST before and after optimization. The results demonstrate that optimized UGS spatial patterns, achieved through a controlled expansion of UGS area, significantly alleviated thermal stress by reducing the total LST by 2,799.82 °C and lowering its standard deviation by 0.04. Industrial zones, densely populated areas, and commercial districts exhibited the most pronounced LST reductions that spatially corresponded to changes in UGS spatial patterns. In addition, post-optimization analysis revealed notable changes in key landscape pattern metrics: patch cohesion index (COHESION), patch density (PD), landscape shape index (LSI), and percent of landscape (PLAND). Compared to pre-optimization conditions, their positive contributions to LST were weakened, while their cooling effects were enhanced. This research provides a “space-for-time” planning paradigm that offers intuitive and actionable decision-making support for urban renewal planners and policymakers.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102320"},"PeriodicalIF":7.1,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From grids to dendrites: Quantifying spatial heterogeneity in urban road networks 从网格到树突：量化城市道路网络的空间异质性

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-03 DOI: 10.1016/j.compenvurbsys.2025.102309

Lin Zhang , Shenhong Li , Yaolin Liu , Haosheng Huang , Nico Van de Weghe

{"title":"From grids to dendrites: Quantifying spatial heterogeneity in urban road networks","authors":"Lin Zhang , Shenhong Li , Yaolin Liu , Haosheng Huang , Nico Van de Weghe","doi":"10.1016/j.compenvurbsys.2025.102309","DOIUrl":"10.1016/j.compenvurbsys.2025.102309","url":null,"abstract":"<div><div>Road network spatial heterogeneity significantly influences urban development and infrastructure efficiency. We present a novel approach using Relational Graph Convolutional Networks (RGCN) to analyze road networks across 58 global cities from 2020 to 2024, introducing Hits@1 as a comprehensive measure of spatial heterogeneity. When nodes (Road intersections) exhibit high spatial heterogeneity, they are more diverse and distinct from each other, making the embedding process more straightforward for the RGCN model. A higher Hits@1 score indicates RGCN can better differentiate between nodes, directly correlating with greater spatial heterogeneity in the road network. Our analysis demonstrates that Hits@1 can effectively distinguish four road network typologies (Dendritic, Grid, Mixed, and Polygonal), with Dendritic networks showing the highest heterogeneity (Hits@1<span><math><mo>≈</mo></math></span>0.57) and Grid networks the lowest (Hits@1<span><math><mo>≈</mo></math></span>0.42). Statistical analysis reveals strong correlations between heterogeneity and urban metrics, including traffic index (R = 0.36), CO2 emissions (R = 0.43), and road density (R = 0.48). Temporal analysis of road evolution shows distinct regional patterns: developing regions trend toward higher heterogeneity, while Western cities demonstrate increasing uniformity. Chinese coastal cities exhibit increasing complexity, contrasting with inland cities’ movement toward organized patterns. These findings validate Hits@1 as an effective metric for understanding road network evolution and provide valuable insights for urban planning.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102309"},"PeriodicalIF":7.1,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maximum unobstructed shortest path between multipart-continuous geometries: Enabling novel type of access evaluations for urban safety 多部分连续几何之间的最大无障碍最短路径：为城市安全提供新型通道评估

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-06-03 DOI: 10.1016/j.compenvurbsys.2025.102308

Jiwon Baik, Alan T. Murray

{"title":"Maximum unobstructed shortest path between multipart-continuous geometries: Enabling novel type of access evaluations for urban safety","authors":"Jiwon Baik, Alan T. Murray","doi":"10.1016/j.compenvurbsys.2025.102308","DOIUrl":"10.1016/j.compenvurbsys.2025.102308","url":null,"abstract":"<div><div>In safety planning, preparing for worst-case scenarios is critical. For instance, fire stations are strategically located aiming to respond within four minutes in the worst-case. Similarly, hydrant-to-structure access adheres to this principle. Fire codes require that the furthest projection on a building's exterior must be within a specified distance from fire access roads via an unobstructed route. This ensures that all parts of a building are reachable by a fire hose from parked fire apparatus. This requirement involves a novel spatial optimization problem: the <em>Maximum Generalized Euclidean shortest path problem</em>. The Euclidean shortest path problem is an approach for determining an unobstructed shortest path, however, constrained to single-point representations for origin and destination. This research generalizes this problem to identify unobstructed paths between multipart-continuous geometries, such as road segments and building structures. A novel solution approach is also proposed, expanding the scope of access evaluation and advocating safety planning.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102308"},"PeriodicalIF":7.1,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the power of CNNs to detect slums in Brazil 关于cnn探测巴西贫民窟的力量

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-05-31 DOI: 10.1016/j.compenvurbsys.2025.102306

João P. da Silva , José F. Rodrigues-Jr , João P. de Albuquerque

{"title":"On the power of CNNs to detect slums in Brazil","authors":"João P. da Silva , José F. Rodrigues-Jr , João P. de Albuquerque","doi":"10.1016/j.compenvurbsys.2025.102306","DOIUrl":"10.1016/j.compenvurbsys.2025.102306","url":null,"abstract":"<div><div>The rapid expansion of slums poses a critical challenge for urban planning in Low- and Middle-Income Countries (LMICs), where traditional data collection methods like censuses are often outdated and insufficient. This study examines the transferability and generalization capabilities of deep learning models, specifically Convolutional Neural Networks (CNNs), for automated slum detection across six Brazilian cities with varying urban morphologies: São Paulo, Rio de Janeiro, Belo Horizonte, Brasília, Salvador, and Porto Alegre. Utilizing Very High Resolution (VHR) and High Resolution (HR) satellite imagery, we trained and evaluated models based on the EfficientNetV2L architecture. Our experimental results show that CNN models trained on data from a single city achieved high accuracy within that city (F1 scores exceeding 0.90 with VHR imagery), but their performance significantly decreased when applied to other cities (F1 scores dropping below 0.80), highlighting the impact of regional variations in urban morphology. Conversely, a generalized model trained on combined data from all six cities maintained robust performance across all cities, achieving F1 scores above 0.80 with VHR imagery. These findings indicate that while CNNs are effective for automated slum mapping, regional diversity necessitates training on diverse datasets to ensure generalization. We provide a comprehensive methodology over an openly shared dataset, and code to facilitate future research and applications in urban geoscience. The aim is to enhance the scalability and generalization of remote sensing and deep learning methods for slum identification across diverse urban environments.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102306"},"PeriodicalIF":7.1,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Torque work of origin-destination flows: Quantifying urban place centrality from a physical perspective 起点-终点流的扭矩功：从物理角度量化城市场所中心性

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-05-31 DOI: 10.1016/j.compenvurbsys.2025.102311

Xiaorui Yan , Tao Pei , Ci Song , Zidong Fang , Xiaohan Liu , Tianyu Liu , Linfeng Jiang , Ying Gao , Guangdong Li , Jie Huang , Yaqin Sun

{"title":"Torque work of origin-destination flows: Quantifying urban place centrality from a physical perspective","authors":"Xiaorui Yan , Tao Pei , Ci Song , Zidong Fang , Xiaohan Liu , Tianyu Liu , Linfeng Jiang , Ying Gao , Guangdong Li , Jie Huang , Yaqin Sun","doi":"10.1016/j.compenvurbsys.2025.102311","DOIUrl":"10.1016/j.compenvurbsys.2025.102311","url":null,"abstract":"<div><div>Quantifying urban place centrality, defined as its relative importance in serving its peripheral areas, provides insights into urban structures, optimizes resource allocation, and supports strategic urban planning. Centrality is shaped by three aspects: service volume, spatial reach, and directional diversity. However, existing measures often assess these factors separately and few integrate them simultaneously. Additionally, centrality analyses often overlook local perspectives and intra-day dynamics. To this end, we propose a novel origin-destination flow-based centrality measure, namely Total Torque Work (TTW), that integrates these three aspects into a single value, conceptualized as “Torque work of flow”, where flow volume, length, and direction correspond to the force magnitude, lever arm, and angular displacement. The effectiveness of the TTW is validated by simulation experiments. We apply this measure to analyze macro- and micro-centralities in Beijing, using taxi and shared bike flow data. Macro-centrality shows a monocentric structure, with higher values near railway stations, airports, and business and commercial centers. Micro-centrality is more polycentric, with subway stations exhibiting higher centrality. Time series clustering identifies three temporal patterns in both macro- and micro-centralities: two “daytime-dominant” patterns linked to multifunctional activities and commuting, and a “nighttime-dominant” pattern in residential areas. The study concludes with several implications for urban planning, emphasizing the importance of incorporating multi-spatiotemporal scales.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102311"},"PeriodicalIF":7.1,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inclusive Digital Planning – Co-designing a collaborative mapping tool to support the planning of accessible public space for all 包容性数字规划——共同设计一种协作测绘工具，以支持所有人的无障碍公共空间规划

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-05-29 DOI: 10.1016/j.compenvurbsys.2025.102310

Johannes Flacke , Fenna Imara Hoefsloot , Karin Pfeffer

{"title":"Inclusive Digital Planning – Co-designing a collaborative mapping tool to support the planning of accessible public space for all","authors":"Johannes Flacke , Fenna Imara Hoefsloot , Karin Pfeffer","doi":"10.1016/j.compenvurbsys.2025.102310","DOIUrl":"10.1016/j.compenvurbsys.2025.102310","url":null,"abstract":"<div><div>Digital planning is loaded with the expectation to make planning more inclusive. However, digital tools currently used in spatial planning processes to facilitate communication and participation of stakeholders often exclude people with disabilities through their design. Consequently, the research question of this study is how to design digital tools to support inclusive participation in the planning and design of public spaces to make them accessible for all. To answer this question, this research aimed to co-design an inclusive collaborative mapping tool with people with disabilities to enhance their participation in the planning and design of accessible public spaces. Developed in collaboration with eight people with various disabilities from the city of Zwolle in the Netherlands, the open-source mapping tool allows the in-situ registration of accessibility issues and supports collaborative decision-making workshops. The co-design process served to identify barriers and obstacles to the accessibility of public spaces in the city as well as user requirements for the inclusive design of the collaborative mapping tool. The tool was tested and evaluated in a collaborative mapping session with people with disabilities and municipal planners from the case study city. Our findings show that the design of inclusive digital planning tools is not limited to software features but also relates to hardware functionalities and the environment in which a tool is used. Taking the lessons learned from the co-design process, we argue that digital, physical, social and procedural accessibility are key to achieving inclusive digital planning.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102310"},"PeriodicalIF":7.1,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Convolutional neural networks for predicting the perceived density of large urban fabrics 用于预测大型城市结构感知密度的卷积神经网络

IF 7.1 1区地球科学

Computers Environment and Urban Systems Pub Date : 2025-05-22 DOI: 10.1016/j.compenvurbsys.2025.102304

Guy Austern , Roei Yosifof , Tomer Michaeli , Shahar Yadin , Dafna Fisher-Gewirtzman

{"title":"Convolutional neural networks for predicting the perceived density of large urban fabrics","authors":"Guy Austern , Roei Yosifof , Tomer Michaeli , Shahar Yadin , Dafna Fisher-Gewirtzman","doi":"10.1016/j.compenvurbsys.2025.102304","DOIUrl":"10.1016/j.compenvurbsys.2025.102304","url":null,"abstract":"<div><div>Urban density, along with the associated urban morphology and topology, significantly influences human perception, emotions, and behavior, ultimately affecting our overall well-being. Over the past decades, experts have developed spatial analysis models and tools which evaluate how planning and design impact urban residents and the functionality of cities. One such spatial analyses model is the Urban Spatial Openness Index (USOI) which utilizes ray-casting to conduct 3D visibility analysis predicting the perceived density of entire cities on a macro-scale, represented as 2D heatmaps. In the urban scale, ray-casting analysis is computationally intense and requires significant resources, which hinders its effective application. In this paper, we use a Convolutional Neural Network (CNN) to train a model to predict perceived density in urban fabrics based on 2D heatmap images. The processes described in this paper include creating a dataset of corresponding USOI images and height images from several different cities, training a CNN model, and evaluating the model's performance. The model predicts USOI with a mean absolute error of 1.92 %, which is considered highly accurate for visual perception on the urban scale. This study showcases the capability of CNN models to predict perceived density as measured by the USOI. The use of a predictive model can significantly reduce the processing time of 3D visibility analysis on the urban scale.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102304"},"PeriodicalIF":7.1,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144114848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0