Pub Date : 2025-09-01Epub Date: 2025-05-12DOI: 10.1016/j.compenvurbsys.2025.102305
Mark Birkin , Patrick Ballantyne , Seth Bullock , Alison Heppenstall , Heeseo Kwon , Nick Malleson , Jing Yao , Anna Zanchetta
The paper discusses the relevance of the latest advances in data science and artificial intelligence for urban systems research. It has a particular focus on the importance of recent innovations in the context of ‘wicked’ urban problems which continue to confront decision-makers within practical policy settings. It is argued that the latest advances in AI such as large language models offer the potential for transformative research, but only if properly specified within the unique and distinctive context of geographical space. The idea of a digital twin requires careful articulation to support the management of expectations and appropriate alignment within a social setting. At the end of the day, AI is not a panacea for the problems of cities, nor is it a substitute for imaginative policy design or interventions through consensus and good government. However in a world which is characterised by vast riches of data alongside enormous complexity of process, the investment in new tools and methods is a social and intellectual imperative in driving human understanding to new levels.
{"title":"Digital twins and AI for healthy and sustainable cities","authors":"Mark Birkin , Patrick Ballantyne , Seth Bullock , Alison Heppenstall , Heeseo Kwon , Nick Malleson , Jing Yao , Anna Zanchetta","doi":"10.1016/j.compenvurbsys.2025.102305","DOIUrl":"10.1016/j.compenvurbsys.2025.102305","url":null,"abstract":"<div><div>The paper discusses the relevance of the latest advances in data science and artificial intelligence for urban systems research. It has a particular focus on the importance of recent innovations in the context of ‘wicked’ urban problems which continue to confront decision-makers within practical policy settings. It is argued that the latest advances in AI such as large language models offer the potential for transformative research, but only if properly specified within the unique and distinctive context of geographical space. The idea of a digital twin requires careful articulation to support the management of expectations and appropriate alignment within a social setting. At the end of the day, AI is not a panacea for the problems of cities, nor is it a substitute for imaginative policy design or interventions through consensus and good government. However in a world which is characterised by vast riches of data alongside enormous complexity of process, the investment in new tools and methods is a social and intellectual imperative in driving human understanding to new levels.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102305"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936557","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}
Pub Date : 2025-09-01Epub Date: 2025-04-30DOI: 10.1016/j.compenvurbsys.2025.102299
Xinglei Wang , Tao Cheng , Stephen Law , Zichao Zeng , Lu Yin , Junyuan Liu
Understanding and characterising urban environment is crucial for urban planning and geospatial analysis. One common approach to this process is through using point of interest (POI) data, which offers rich information about the spatial-semantic characteristics of urban spaces. Existing methods for learning urban space representations from POIs face several limitations, including reliance on predefined spatial units, ignorance of POI location information, underutilisation of POI semantic attributes, and computational inefficiencies. To address these gaps, we propose CaLLiPer (Contrastive Language-Location Pre-training), a novel approach that directly embeds continuous urban spaces into vector representations that capture the spatial and semantic characteristics of urban environment. This model leverages multimodal contrastive learning to align location embeddings with textual descriptions of POIs, bypassing the need for complex training corpus construction and negative sampling. Applying CaLLiPer to learning urban space representations in London, UK, we demonstrate 5–15% improvement in predictive performance for land use classification and socioeconomic mapping tasks compared to state-of-the-art methods. Visualisations and correlation analysis of the learned representations further verify our model's ability to capture spatial variations in urban semantics with high accuracy and fine resolution. Moreover, CaLLiPer achieves reduced training time, showcasing its efficiency and scalability. Additional experiments demonstrate the robustness of our model across different spatial scales and urban context. Notably, the experiment on Singapore showed an improvement of over 20%. This work also provides a promising pathway for scalable, semantically rich urban space representation learning that can support the development of geospatial foundation models. The implementation code is available at https://github.com/xlwang233/CaLLiPer.
{"title":"Multi-modal contrastive learning of urban space representations from POI data","authors":"Xinglei Wang , Tao Cheng , Stephen Law , Zichao Zeng , Lu Yin , Junyuan Liu","doi":"10.1016/j.compenvurbsys.2025.102299","DOIUrl":"10.1016/j.compenvurbsys.2025.102299","url":null,"abstract":"<div><div>Understanding and characterising urban environment is crucial for urban planning and geospatial analysis. One common approach to this process is through using point of interest (POI) data, which offers rich information about the spatial-semantic characteristics of urban spaces. Existing methods for learning urban space representations from POIs face several limitations, including reliance on predefined spatial units, ignorance of POI location information, underutilisation of POI semantic attributes, and computational inefficiencies. To address these gaps, we propose CaLLiPer (<u><strong>C</strong></u>ontr<u><strong>a</strong></u>stive <u><strong>L</strong></u>anguage-<u><strong>L</strong></u>ocat<u><strong>i</strong></u>on <u><strong>P</strong></u>r<strong>e</strong>-t<u><strong>r</strong></u>aining), a novel approach that directly embeds continuous urban spaces into vector representations that capture the spatial and semantic characteristics of urban environment. This model leverages multimodal contrastive learning to align location embeddings with textual descriptions of POIs, bypassing the need for complex training corpus construction and negative sampling. Applying CaLLiPer to learning urban space representations in London, UK, we demonstrate 5–15% improvement in predictive performance for land use classification and socioeconomic mapping tasks compared to state-of-the-art methods. Visualisations and correlation analysis of the learned representations further verify our model's ability to capture spatial variations in urban semantics with high accuracy and fine resolution. Moreover, CaLLiPer achieves reduced training time, showcasing its efficiency and scalability. Additional experiments demonstrate the robustness of our model across different spatial scales and urban context. Notably, the experiment on Singapore showed an improvement of over 20%. This work also provides a promising pathway for scalable, semantically rich urban space representation learning that can support the development of geospatial foundation models. The implementation code is available at <span><span>https://github.com/xlwang233/CaLLiPer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102299"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886865","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}
Pub Date : 2025-09-01Epub Date: 2025-04-17DOI: 10.1016/j.compenvurbsys.2025.102291
Pilvi Nummi , Anni Hapuoja
The digitalization of urban planning entails a shift to information model-based planning, where plans are produced in a machine-readable and interoperable format. In Finland, a nationally interoperable information model for land use plans has been applied for the first time to digital planning tools in the recently completed project KAATIO. In this article, we apply socio-technical approach to assess how co-development in this project was perceived by municipal planners and software developers, and how did the tools developed meet the needs of planners and planning practice. The results show that a technology-driven culture dominates the national development and hampers the socio-technical approach. Despite the challenges, co-development is beneficial for both software developers and municipal actors. In conclusion, we argue that, in this context, empowering users, facilitating the discussion on information model-based planning, future-oriented understanding of planning tasks, and accepting the diversity of practices while harmonizing the plan data are essential for promoting human factors in the development.
{"title":"Does co-development facilitate achieving useful planning tools? A socio-technical approach to the development of information model-based land use planning in Finland","authors":"Pilvi Nummi , Anni Hapuoja","doi":"10.1016/j.compenvurbsys.2025.102291","DOIUrl":"10.1016/j.compenvurbsys.2025.102291","url":null,"abstract":"<div><div>The digitalization of urban planning entails a shift to information model-based planning, where plans are produced in a machine-readable and interoperable format. In Finland, a nationally interoperable information model for land use plans has been applied for the first time to digital planning tools in the recently completed project KAATIO. In this article, we apply socio-technical approach to assess how co-development in this project was perceived by municipal planners and software developers, and how did the tools developed meet the needs of planners and planning practice. The results show that a technology-driven culture dominates the national development and hampers the socio-technical approach. Despite the challenges, co-development is beneficial for both software developers and municipal actors. In conclusion, we argue that, in this context, empowering users, facilitating the discussion on information model-based planning, future-oriented understanding of planning tasks, and accepting the diversity of practices while harmonizing the plan data are essential for promoting human factors in the development.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102291"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847917","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}
Pub Date : 2025-09-01Epub Date: 2025-04-28DOI: 10.1016/j.compenvurbsys.2025.102300
Kang Zou , Xinyu Yu , Coco Yin Tung Kwok , Man Sing Wong , Mei-Po Kwan , Huiying (Cynthia) Hou
Traffic noise poses a globally significant environmental threat to urban livability, particularly in high-density areas where conventional noise assessment methods struggle to capture dynamic spatio-temporal variations. The Minimal Error Iterative Model based on Diversion Strategies (MEI-DS) was proposed in this study to derive high-resolution traffic flow networks with overcoming temporal granularity limitations. A case study in Hong Kong, China, a high-density building environment city was conducted to examine the model performance, with an average relative error of 0.48 %. Afterwards, a novel noise assessment framework was developed by integrating MEI-DS-generated flows with noise source model and 3D noise propagation model. This approach reveals striking spatiotemporal heterogeneities: Peak noise levels occur between 08:00–09:00 on weekdays, while Saturdays show persistently high noise levels from 09:00 to 20:00. Sundays exhibit minimal diurnal noise fluctuations. Multi-scale assessments (city-district-building-individual) reveal 85.9 % of the population experiences noise exposure exceeding WHO-recommended thresholds. This study offers actionable insights to inform urban planning and develop health-centric strategies for mitigating traffic noise, and the proposed model can also be transferred to other regions with strong potential to address the impact of traffic noise on environmental health.
{"title":"Simulation and exposure assessment of hourly traffic noise in Hong Kong using a minimal error iterative model based on diversion strategies","authors":"Kang Zou , Xinyu Yu , Coco Yin Tung Kwok , Man Sing Wong , Mei-Po Kwan , Huiying (Cynthia) Hou","doi":"10.1016/j.compenvurbsys.2025.102300","DOIUrl":"10.1016/j.compenvurbsys.2025.102300","url":null,"abstract":"<div><div>Traffic noise poses a globally significant environmental threat to urban livability, particularly in high-density areas where conventional noise assessment methods struggle to capture dynamic spatio-temporal variations. The Minimal Error Iterative Model based on Diversion Strategies (MEI-DS) was proposed in this study to derive high-resolution traffic flow networks with overcoming temporal granularity limitations. A case study in Hong Kong, China, a high-density building environment city was conducted to examine the model performance, with an average relative error of 0.48 %. Afterwards, a novel noise assessment framework was developed by integrating MEI-DS-generated flows with noise source model and 3D noise propagation model. This approach reveals striking spatiotemporal heterogeneities: Peak noise levels occur between 08:00–09:00 on weekdays, while Saturdays show persistently high noise levels from 09:00 to 20:00. Sundays exhibit minimal diurnal noise fluctuations. Multi-scale assessments (city-district-building-individual) reveal 85.9 % of the population experiences noise exposure exceeding WHO-recommended thresholds. This study offers actionable insights to inform urban planning and develop health-centric strategies for mitigating traffic noise, and the proposed model can also be transferred to other regions with strong potential to address the impact of traffic noise on environmental health.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102300"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143878796","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}
Pub Date : 2025-09-01Epub Date: 2025-05-16DOI: 10.1016/j.compenvurbsys.2025.102307
Haotian Wang, Zidong Yu, Xintao Liu
The impact of sensory experiences on physical and mental health in urban environments has gained significant attention, particularly the influence of soundscapes in waterfronts development. This study employed social media data from Twitter to quantitatively analyse the soundscape of Hong Kong Victoria Harbour waterfronts, offering a novel perspective in urban sensory research. Through comparative analysis between tourists and residents, it uncovered how different groups perceive soundscapes in these specific urban waterfronts setting. Utilizing a two-step analytical approach—initially applying rank-size distribution and mean difference index—this study mapped the spatial distribution of soundscapes and used global and local regression models to explore their correlations with key urban features such as building density, population density, and ethnic diversity. The findings revealed distinct spatial patterns in how soundscapes are experienced by tourists and residents at the Victoria Harbour waterfronts, influenced significantly by the built environment. For instance, while residents experience negative auditory sensory in high building density areas, tourists perceive these areas positively. Furthermore, this research underscored the differing correlations of population density on soundscape experience among these groups. Residents enjoy positive soundscape connections in bustling areas, whereas tourists prefer quieter environments. Moreover, the research also found the differences in how residents and tourists accept multicultural soundscapes. This study not only contributed theoretically by linking soundscapes to urban and socio-economic variables but also demonstrated the potential of social media data as a tool for studying urban sensory. The study findings could offer insights that are relevant to planning and design of urban waterfronts.
{"title":"Deciphering Urban Soundscapes: A study of sensory experiences at Hong Kong Victoria harbour waterfronts using social media","authors":"Haotian Wang, Zidong Yu, Xintao Liu","doi":"10.1016/j.compenvurbsys.2025.102307","DOIUrl":"10.1016/j.compenvurbsys.2025.102307","url":null,"abstract":"<div><div>The impact of sensory experiences on physical and mental health in urban environments has gained significant attention, particularly the influence of soundscapes in waterfronts development. This study employed social media data from Twitter to quantitatively analyse the soundscape of Hong Kong Victoria Harbour waterfronts, offering a novel perspective in urban sensory research. Through comparative analysis between tourists and residents, it uncovered how different groups perceive soundscapes in these specific urban waterfronts setting. Utilizing a two-step analytical approach—initially applying rank-size distribution and mean difference index—this study mapped the spatial distribution of soundscapes and used global and local regression models to explore their correlations with key urban features such as building density, population density, and ethnic diversity. The findings revealed distinct spatial patterns in how soundscapes are experienced by tourists and residents at the Victoria Harbour waterfronts, influenced significantly by the built environment. For instance, while residents experience negative auditory sensory in high building density areas, tourists perceive these areas positively. Furthermore, this research underscored the differing correlations of population density on soundscape experience among these groups. Residents enjoy positive soundscape connections in bustling areas, whereas tourists prefer quieter environments. Moreover, the research also found the differences in how residents and tourists accept multicultural soundscapes. This study not only contributed theoretically by linking soundscapes to urban and socio-economic variables but also demonstrated the potential of social media data as a tool for studying urban sensory. The study findings could offer insights that are relevant to planning and design of urban waterfronts.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102307"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071157","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}
Pub Date : 2025-09-01Epub Date: 2025-05-09DOI: 10.1016/j.compenvurbsys.2025.102302
Tianhong Zhao , Xiucheng Liang , Filip Biljecki , Wei Tu , Jinzhou Cao , Xiaojiang Li , Shengao Yi
Street view imagery (SVI), with its rich visual information, is increasingly recognized as a valuable data source for urban research. Particularly, by leveraging computer vision techniques, SVI can be used to calculate various urban form indices (e.g., Green View Index, GVI), providing a new approach for large-scale quantitative assessments of urban environments. However, SVI data collected at the same location in different seasons can yield varying urban form indices due to phenological changes, even when the urban form remains constant. Numerous studies overlook this kind of seasonal bias. To address this gap, we propose a systematic analytical framework for quantifying and evaluating seasonal bias in SVI, drawing on more than 262,000 images from 40 cities worldwide. This framework encompasses three aspects: seasonal bias within urban areas, seasonal bias across cities on a global scale, and the impact of seasonal bias in practical applications. The results reveal that (1) seasonal bias is evident, with an average mean absolute percentage error (MAPE) of 54 % for GVI across all sampled cities, and it is particularly pronounced in areas with significant seasonal bias; (2) seasonal bias is strongly correlated with geographic location, with greater bias observed in cities with lower average rainfall and temperatures; and (3) in practical applications, ignoring seasonal bias may result in analytical errors (e.g., an ARI of 0.35 in clustering). By identifying and quantifying seasonal bias in SVI, this study contributes to improving the accuracy of urban environmental assessments based on street view data and provides new theoretical support for the broader application of such data on a global scale.
{"title":"Quantifying seasonal bias in street view imagery for urban form assessment: A global analysis of 40 cities","authors":"Tianhong Zhao , Xiucheng Liang , Filip Biljecki , Wei Tu , Jinzhou Cao , Xiaojiang Li , Shengao Yi","doi":"10.1016/j.compenvurbsys.2025.102302","DOIUrl":"10.1016/j.compenvurbsys.2025.102302","url":null,"abstract":"<div><div>Street view imagery (SVI), with its rich visual information, is increasingly recognized as a valuable data source for urban research. Particularly, by leveraging computer vision techniques, SVI can be used to calculate various urban form indices (e.g., Green View Index, GVI), providing a new approach for large-scale quantitative assessments of urban environments. However, SVI data collected at the same location in different seasons can yield varying urban form indices due to phenological changes, even when the urban form remains constant. Numerous studies overlook this kind of seasonal bias. To address this gap, we propose a systematic analytical framework for quantifying and evaluating seasonal bias in SVI, drawing on more than 262,000 images from 40 cities worldwide. This framework encompasses three aspects: seasonal bias within urban areas, seasonal bias across cities on a global scale, and the impact of seasonal bias in practical applications. The results reveal that (1) seasonal bias is evident, with an average mean absolute percentage error (MAPE) of 54 % for GVI across all sampled cities, and it is particularly pronounced in areas with significant seasonal bias; (2) seasonal bias is strongly correlated with geographic location, with greater bias observed in cities with lower average rainfall and temperatures; and (3) in practical applications, ignoring seasonal bias may result in analytical errors (e.g., an ARI of 0.35 in clustering). By identifying and quantifying seasonal bias in SVI, this study contributes to improving the accuracy of urban environmental assessments based on street view data and provides new theoretical support for the broader application of such data on a global scale.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102302"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923716","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}
Pub Date : 2025-09-01Epub Date: 2025-05-12DOI: 10.1016/j.compenvurbsys.2025.102290
Matthew Wigginton Bhagat-Conway , Audrey Compiano , E. Irene Ivie
Post-war suburban development is often characterized by a disconnected pod-and-collector street pattern. This creates significant barriers to active travel, forcing even short trips to take roundabout routes on busy arterial roads. However, it also creates a network of low-stress neighborhood streets. We hypothesize that there are many opportunities to add short, low-cost pedestrian and bicycle links to these street networks to increase connectivity.
A key challenge is identifying these links. While planners have a good idea of where major infrastructure investments are beneficial, they are unlikely to be familiar with every neighborhood street and potential connections between them. We introduce an algorithm to automatically and efficiently identify potential new links based only on existing network topology, with no need to prespecify potential projects. We score these links based on their contribution to accessibility. We apply this algorithm to the pedestrian network of Charlotte, North Carolina, USA, and find opportunities to improve connectivity through new links and safe crossings of major roads.
{"title":"So close, yet so far: A new method for identification of high-impact missing links in pedestrian networks","authors":"Matthew Wigginton Bhagat-Conway , Audrey Compiano , E. Irene Ivie","doi":"10.1016/j.compenvurbsys.2025.102290","DOIUrl":"10.1016/j.compenvurbsys.2025.102290","url":null,"abstract":"<div><div>Post-war suburban development is often characterized by a disconnected pod-and-collector street pattern. This creates significant barriers to active travel, forcing even short trips to take roundabout routes on busy arterial roads. However, it also creates a network of low-stress neighborhood streets. We hypothesize that there are many opportunities to add short, low-cost pedestrian and bicycle links to these street networks to increase connectivity.</div><div>A key challenge is identifying these links. While planners have a good idea of where major infrastructure investments are beneficial, they are unlikely to be familiar with every neighborhood street and potential connections between them. We introduce an algorithm to automatically and efficiently identify potential new links based only on existing network topology, with no need to prespecify potential projects. We score these links based on their contribution to accessibility. We apply this algorithm to the pedestrian network of Charlotte, North Carolina, USA, and find opportunities to improve connectivity through new links and safe crossings of major roads.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102290"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936556","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}
Pub Date : 2025-09-01Epub Date: 2025-05-03DOI: 10.1016/j.compenvurbsys.2025.102301
Bo Li, Ali Mostafavi
A growing body of literature has recognized the importance of characterizing infrastructure inequality in cities and provided quantified metrics to inform urban development plans. However, the majority of existing approaches suffered from two limitations. First, prior research has provided empirical evidence of negative environmental impacts that infrastructure can incur, while infrastructure provision inequality assessment has not taken those environmental concerns into consideration. Second, comprehensive provision assessment for multi-infrastructure system calls for a proper weight assignment, while current studies either determine the infrastructure components as equal weights or rely on subjective methods (e.g. AHP), which may be affected by potential biases. This study proposes a novel approach for incorporating environmental considerations into quantifying and assessing infrastructure provision in cities based on a data-driven method. We applied an interpretable machine learning method (XGBoost + SHAP) to capture the relationship between infrastructure features and environmental hazards (i.e., air pollution and urban heat), and then determined feature weights as their relative contributions towards environmental hazards when calculating infrastructure provision. The implementation of the model in five metropolitan areas in the U.S. demonstrates the capability of the proposed approach in characterizing inequality in infrastructure. Further the study reveals both spatial and income inequality regarding infrastructure provision. Environmentally integrated infrastructure provision proposed in this study can better capture the intersection of infrastructure development and environmental justice in measuring and characterizing infrastructure inequality in cities. This study could be used effectively to inform integrated urban design strategies to promote infrastructure equity and environmental justice based on data-driven and machine learning-based insights.
{"title":"Incorporating environmental considerations into infrastructure inequality evaluation using interpretable machine learning","authors":"Bo Li, Ali Mostafavi","doi":"10.1016/j.compenvurbsys.2025.102301","DOIUrl":"10.1016/j.compenvurbsys.2025.102301","url":null,"abstract":"<div><div>A growing body of literature has recognized the importance of characterizing infrastructure inequality in cities and provided quantified metrics to inform urban development plans. However, the majority of existing approaches suffered from two limitations. First, prior research has provided empirical evidence of negative environmental impacts that infrastructure can incur, while infrastructure provision inequality assessment has not taken those environmental concerns into consideration. Second, comprehensive provision assessment for multi-infrastructure system calls for a proper weight assignment, while current studies either determine the infrastructure components as equal weights or rely on subjective methods (e.g. AHP), which may be affected by potential biases. This study proposes a novel approach for incorporating environmental considerations into quantifying and assessing infrastructure provision in cities based on a data-driven method. We applied an interpretable machine learning method (XGBoost + SHAP) to capture the relationship between infrastructure features and environmental hazards (i.e., air pollution and urban heat), and then determined feature weights as their relative contributions towards environmental hazards when calculating infrastructure provision. The implementation of the model in five metropolitan areas in the U.S. demonstrates the capability of the proposed approach in characterizing inequality in infrastructure. Further the study reveals both spatial and income inequality regarding infrastructure provision. Environmentally integrated infrastructure provision proposed in this study can better capture the intersection of infrastructure development and environmental justice in measuring and characterizing infrastructure inequality in cities. This study could be used effectively to inform integrated urban design strategies to promote infrastructure equity and environmental justice based on data-driven and machine learning-based insights.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"120 ","pages":"Article 102301"},"PeriodicalIF":7.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901960","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}
Pub Date : 2025-09-01Epub Date: 2025-05-22DOI: 10.1016/j.compenvurbsys.2025.102304
Guy Austern , Roei Yosifof , Tomer Michaeli , Shahar Yadin , Dafna Fisher-Gewirtzman
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.
{"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":"2025-09-01","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}
To evaluate human exposure to environmental factors, sufficient population-targeted sensing power of sensor carriers is crucial. However, the traditional static sensing approach is constrained by its limited coverage. Recently, equipping moving vehicles with sensors has emerged as a new approach. However, a quantitative comparison between mobile and traditional static sensing is still lacking. Using empirical taxi trajectory and population data in Beijing and Xiamen, we found that while a small number of taxi-based mobile sensors can cover a larger portion of the population, well-located static sensors eventually surpass mobile sensors in coverage as their number increases. In addition, a higher required frequency reduces the coverage of mobile sensors, whereas a higher cost ratio between static and mobile sensors reduces the coverage of static sites. Taxis provide extensive spatial coverage but with some uncertainty, especially in peripheral areas, whereas static sensors ensure localized and stable coverage. Based on the advantage of taxis and static sites, we propose an effective greedy-add-guided strengthen elitist genetic algorithm to determine the optimal combination of static and mobile sensors. The key idea is to position static sensors in areas with relatively low taxi visit probabilities but high population density. The results indicate that this optimal combination achieves higher population coverage compared to using taxis alone. It addresses the uncertainty in taxi coverage and significantly reduces the number of sensors required. These results support the feasibility of using taxis as a sensing paradigm and further highlight the potential of combining these two sensing paradigms in population-targeted sensing applications.
{"title":"Advancing population-targeted urban sensing: A comparative study on mobile and static sensing paradigms","authors":"Yuan-Qiao Hou , Xiao-Jian Chen , Zhou Huang , Xia Peng , Yu Liu","doi":"10.1016/j.compenvurbsys.2025.102288","DOIUrl":"10.1016/j.compenvurbsys.2025.102288","url":null,"abstract":"<div><div>To evaluate human exposure to environmental factors, sufficient population-targeted sensing power of sensor carriers is crucial. However, the traditional static sensing approach is constrained by its limited coverage. Recently, equipping moving vehicles with sensors has emerged as a new approach. However, a quantitative comparison between mobile and traditional static sensing is still lacking. Using empirical taxi trajectory and population data in Beijing and Xiamen, we found that while a small number of taxi-based mobile sensors can cover a larger portion of the population, well-located static sensors eventually surpass mobile sensors in coverage as their number increases. In addition, a higher required frequency reduces the coverage of mobile sensors, whereas a higher cost ratio between static and mobile sensors reduces the coverage of static sites. Taxis provide extensive spatial coverage but with some uncertainty, especially in peripheral areas, whereas static sensors ensure localized and stable coverage. Based on the advantage of taxis and static sites, we propose an effective greedy-add-guided strengthen elitist genetic algorithm to determine the optimal combination of static and mobile sensors. The key idea is to position static sensors in areas with relatively low taxi visit probabilities but high population density. The results indicate that this optimal combination achieves higher population coverage compared to using taxis alone. It addresses the uncertainty in taxi coverage and significantly reduces the number of sensors required. These results support the feasibility of using taxis as a sensing paradigm and further highlight the potential of combining these two sensing paradigms in population-targeted sensing applications.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"119 ","pages":"Article 102288"},"PeriodicalIF":7.1,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143791196","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号