Computers Environment and Urban Systems最新文献_第5页

Deep contrastive learning for feature alignment: Insights from housing-household relationship inference 特征对齐的深度对比学习：来自住房-家庭关系推断的见解

IF 8.3 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-08-03 DOI: 10.1016/j.compenvurbsys.2025.102328

Xiao Qian, Shangjia Dong, Rachel Davidson

Housing and household characteristics are key determinants of social and economic well-being, yet our understanding of their interrelationships remains limited. This study addresses this knowledge gap by developing a deep contrastive learning (DCL) model to infer housing-household relationships using the American Community Survey (ACS) Public Use Microdata Sample (PUMS). More broadly, the proposed model is suitable for a class of problems where the goal is to learn joint relationships between two distinct entities without explicitly labeled ground truth data. Our proposed dual-encoder DCL approach leverages co-occurrence patterns in PUMS and introduces a bisect K-means clustering method to overcome the absence of ground truth labels. The dual-encoder DCL architecture is designed to handle the semantic differences between housing (building) and household (people) features while mitigating noise introduced by clustering. To validate the model, we generate a synthetic ground truth dataset and conduct comprehensive evaluations. The model further demonstrates its superior performance in capturing housing-household relationships in Delaware compared to state-of-the-art methods. A transferability test in North Carolina confirms its generalizability across diverse sociodemographic and geographic contexts. Finally, the post-hoc explainable AI analysis using SHAP values reveals that tenure status and mortgage information play a more significant role in housing-household matching than traditionally emphasized factors such as the number of persons and rooms.

住房和家庭特征是社会和经济福祉的关键决定因素，但我们对其相互关系的理解仍然有限。本研究利用美国社区调查（ACS）公共使用微数据样本（PUMS）开发了一个深度对比学习（DCL）模型来推断住房-家庭关系，从而解决了这一知识差距。更广泛地说，所提出的模型适用于一类问题，其目标是学习两个不同实体之间的联合关系，而没有明确标记的基础真值数据。我们提出的双编码器DCL方法利用了PUMS中的共现模式，并引入了一种二分k均值聚类方法来克服缺乏基础真值标签的问题。双编码器DCL架构旨在处理住房（建筑）和家庭（人）特征之间的语义差异，同时减轻聚类带来的噪声。为了验证模型，我们生成了一个合成的地面真实数据集并进行了全面的评估。与最先进的方法相比，该模型进一步证明了其在捕捉特拉华州住房与家庭关系方面的卓越表现。在北卡罗来纳州进行的一项可转移性测试证实了它在不同社会人口和地理背景下的普遍性。最后，使用SHAP值的事后可解释人工智能分析表明，在住房-家庭匹配中，使用权地位和抵押信息比传统上强调的因素（如人数和房间数量）发挥更重要的作用。

{"title":"Deep contrastive learning for feature alignment: Insights from housing-household relationship inference","authors":"Xiao Qian, Shangjia Dong, Rachel Davidson","doi":"10.1016/j.compenvurbsys.2025.102328","DOIUrl":"10.1016/j.compenvurbsys.2025.102328","url":null,"abstract":"<div><div>Housing and household characteristics are key determinants of social and economic well-being, yet our understanding of their interrelationships remains limited. This study addresses this knowledge gap by developing a deep contrastive learning (DCL) model to infer housing-household relationships using the American Community Survey (ACS) Public Use Microdata Sample (PUMS). More broadly, the proposed model is suitable for a class of problems where the goal is to learn joint relationships between two distinct entities without explicitly labeled ground truth data. Our proposed dual-encoder DCL approach leverages co-occurrence patterns in PUMS and introduces a bisect K-means clustering method to overcome the absence of ground truth labels. The dual-encoder DCL architecture is designed to handle the semantic differences between housing (building) and household (people) features while mitigating noise introduced by clustering. To validate the model, we generate a synthetic ground truth dataset and conduct comprehensive evaluations. The model further demonstrates its superior performance in capturing housing-household relationships in Delaware compared to state-of-the-art methods. A transferability test in North Carolina confirms its generalizability across diverse sociodemographic and geographic contexts. Finally, the post-hoc explainable AI analysis using SHAP values reveals that tenure status and mortgage information play a more significant role in housing-household matching than traditionally emphasized factors such as the number of persons and rooms.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102328"},"PeriodicalIF":8.3,"publicationDate":"2025-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144764047","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

Urban planning in the age of large language models: Assessing OpenAI o1's performance and capabilities across 556 tasks 大型语言模型时代的城市规划：评估OpenAI 01在556个任务中的性能和能力

IF 8.3 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-08-01 DOI: 10.1016/j.compenvurbsys.2025.102332

Xukai Zhao , He Huang , Tao Yang , Yuxing Lu , Lu Zhang , Ruoyu Wang , Zhengliang Liu , Tianyang Zhong , Tianming Liu

Integrating Large Language Models (LLMs) into urban planning presents significant opportunities to enhance efficiency and support data-driven city development strategies. Despite their potential, the specific capabilities of LLMs within the urban planning context remain underexplored, and the field lacks standardized benchmarks for systematic evaluation. This study presents the first comprehensive evaluation focused on OpenAI o1's performance and capabilities in urban planning, systematically benchmarking it against GPT-3.5 and GPT-4o using an original open-source benchmark comprising 556 tasks across five critical categories: urban planning documentation, examinations, routine data analysis, AI algorithm support, and thesis writing. Through rigorous testing and manual analysis of 170,627 words of generated output, OpenAI o1 consistently outperformed its counterparts, achieving an average performance score of 84.08 % compared to 69.30 % for GPT-4o and 45.27 % for GPT-3.5. Our findings highlight o1's strengths in domain knowledge mastery, basic operational competence, and coding capabilities, demonstrating its potential applications in information retrieval, urban data analytics, planning decision support, educational assistance, and LLM-based agent development. However, significant limitations were identified, including inability in urban design, susceptibility to fabricating information, moderate academic writing quality, challenges in high-level professional examinations, and spatial reasoning, and limited support for specialized or emerging AI algorithms. Future optimizations should prioritize enhancing multimodal integration, implementing robust validation mechanisms, adopting adaptive learning strategies, and enabling domain-specific fine-tuning to meet urban planners' specialized needs. These advancements would enable LLMs to better support the evolving demands of urban planning, allowing professionals to focus more on strategic decision-making and the creative aspects of the field.

将大型语言模型（llm）整合到城市规划中，为提高效率和支持数据驱动的城市发展战略提供了重要机会。尽管具有潜力，法学硕士在城市规划背景下的具体能力仍未得到充分探索，该领域缺乏系统评估的标准化基准。本研究首次对OpenAI o1在城市规划中的性能和能力进行了全面评估，使用原始的开源基准对其进行了系统的基准测试，该基准测试包括五个关键类别的556个任务：城市规划文档、考试、常规数据分析、人工智能算法支持和论文写作。通过对生成输出的170,627个单词的严格测试和人工分析，OpenAI 01始终优于同类产品，平均性能得分为84.08%，而gpt - 40和GPT-3.5的平均性能得分分别为69.30%和45.27%。我们的研究结果突出了o1在领域知识掌握、基本操作能力和编码能力方面的优势，展示了它在信息检索、城市数据分析、规划决策支持、教育辅助和基于llm的代理开发方面的潜在应用。然而，我们发现了显著的局限性，包括城市设计能力不足、易受虚假信息的影响、学术写作质量不高、在高水平专业考试和空间推理方面面临挑战，以及对专业或新兴人工智能算法的支持有限。未来的优化应优先考虑增强多模态集成，实现稳健的验证机制，采用自适应学习策略，并使特定领域的微调能够满足城市规划者的专门需求。这些进步将使法学硕士能够更好地支持城市规划不断变化的需求，使专业人员能够更多地关注该领域的战略决策和创造性方面。

{"title":"Urban planning in the age of large language models: Assessing OpenAI o1's performance and capabilities across 556 tasks","authors":"Xukai Zhao , He Huang , Tao Yang , Yuxing Lu , Lu Zhang , Ruoyu Wang , Zhengliang Liu , Tianyang Zhong , Tianming Liu","doi":"10.1016/j.compenvurbsys.2025.102332","DOIUrl":"10.1016/j.compenvurbsys.2025.102332","url":null,"abstract":"<div><div>Integrating Large Language Models (LLMs) into urban planning presents significant opportunities to enhance efficiency and support data-driven city development strategies. Despite their potential, the specific capabilities of LLMs within the urban planning context remain underexplored, and the field lacks standardized benchmarks for systematic evaluation. This study presents the first comprehensive evaluation focused on OpenAI o1's performance and capabilities in urban planning, systematically benchmarking it against GPT-3.5 and GPT-4o using an original open-source benchmark comprising 556 tasks across five critical categories: urban planning documentation, examinations, routine data analysis, AI algorithm support, and thesis writing. Through rigorous testing and manual analysis of 170,627 words of generated output, OpenAI o1 consistently outperformed its counterparts, achieving an average performance score of 84.08 % compared to 69.30 % for GPT-4o and 45.27 % for GPT-3.5. Our findings highlight o1's strengths in domain knowledge mastery, basic operational competence, and coding capabilities, demonstrating its potential applications in information retrieval, urban data analytics, planning decision support, educational assistance, and LLM-based agent development. However, significant limitations were identified, including inability in urban design, susceptibility to fabricating information, moderate academic writing quality, challenges in high-level professional examinations, and spatial reasoning, and limited support for specialized or emerging AI algorithms. Future optimizations should prioritize enhancing multimodal integration, implementing robust validation mechanisms, adopting adaptive learning strategies, and enabling domain-specific fine-tuning to meet urban planners' specialized needs. These advancements would enable LLMs to better support the evolving demands of urban planning, allowing professionals to focus more on strategic decision-making and the creative aspects of the field.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102332"},"PeriodicalIF":8.3,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144748888","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

Analyzing public response to wildfires: A socio-spatial study using SIR models and NLP techniques 分析公众对野火的反应：使用SIR模型和NLP技术的社会空间研究

IF 8.3 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-08-01 DOI: 10.1016/j.compenvurbsys.2025.102333

Zihui Ma , Guangxiao Hu , Ting-Syuan Lin , Lingyao Li , Songhua Hu , Loni Hagen , Gregory B. Baecher

The increasing frequency and severity of wildfires pose significant risks to communities, infrastructure, and the environment, especially in Wildland-Urban Interface (WUI) areas. Effective disaster management requires understanding how the public perceives and responds to wildfire threats in near-real-time. This study uses social media data to assess public responses (including collective perceptions/reactions) and explores how these responses are linked to city-level community characteristics. Specifically, we leveraged a transformer-based topic modeling technique called BERTopic to identify wildfire response-related topics and then utilized the Susceptible-Infectious-Recovered (SIR) model to compute two key metrics — public response awareness and resilience indicators. Additionally, we used GIS-based spatial analysis to map wildfire responses and the relationships with four groups of city-level factors (racial/ethnic, socioeconomic, demographic, and wildfire-specific). Our findings reveal significant geographic and socio-spatial differences in public responses. Southern California cities with larger Hispanic populations demonstrate higher wildfire awareness and resilience. In contrast, urbanized regions in Central and Northern California exhibit lower awareness levels. Furthermore, resilience is negatively correlated with unemployment rates, particularly in southern regions where higher unemployment aligns with reduced resilience. These findings highlight the need for targeted and equitable wildfire management strategies to improve the adaptive capacity of WUI communities.

野火发生的频率和严重程度日益增加，对社区、基础设施和环境构成了重大风险，特别是在荒地-城市交界地区。有效的灾害管理需要了解公众如何近乎实时地感知和应对野火威胁。本研究使用社交媒体数据来评估公众的反应（包括集体的看法/反应），并探讨这些反应如何与城市层面的社区特征联系起来。具体来说，我们利用一种名为BERTopic的基于变压器的主题建模技术来识别与野火响应相关的主题，然后利用易感-感染-恢复（SIR）模型来计算两个关键指标——公众响应意识和恢复指标。此外，我们使用基于gis的空间分析来绘制野火响应及其与四组城市层面因素（种族/民族、社会经济、人口统计学和野火特异性）的关系。我们的研究结果揭示了公众反应的显著地理和社会空间差异。西班牙裔人口较多的南加州城市表现出更高的野火意识和恢复能力。相比之下，加州中部和北部的城市化地区表现出较低的意识水平。此外，弹性与失业率呈负相关，特别是在南部地区，高失业率与弹性降低相一致。这些发现强调需要有针对性和公平的野火管理战略，以提高WUI社区的适应能力。

{"title":"Analyzing public response to wildfires: A socio-spatial study using SIR models and NLP techniques","authors":"Zihui Ma , Guangxiao Hu , Ting-Syuan Lin , Lingyao Li , Songhua Hu , Loni Hagen , Gregory B. Baecher","doi":"10.1016/j.compenvurbsys.2025.102333","DOIUrl":"10.1016/j.compenvurbsys.2025.102333","url":null,"abstract":"<div><div>The increasing frequency and severity of wildfires pose significant risks to communities, infrastructure, and the environment, especially in Wildland-Urban Interface (WUI) areas. Effective disaster management requires understanding how the public perceives and responds to wildfire threats in near-real-time. This study uses social media data to assess public responses (including collective perceptions/reactions) and explores how these responses are linked to city-level community characteristics. Specifically, we leveraged a transformer-based topic modeling technique called BERTopic to identify wildfire response-related topics and then utilized the Susceptible-Infectious-Recovered (SIR) model to compute two key metrics — public response awareness and resilience indicators. Additionally, we used GIS-based spatial analysis to map wildfire responses and the relationships with four groups of city-level factors (racial/ethnic, socioeconomic, demographic, and wildfire-specific). Our findings reveal significant geographic and socio-spatial differences in public responses. Southern California cities with larger Hispanic populations demonstrate higher wildfire awareness and resilience. In contrast, urbanized regions in Central and Northern California exhibit lower awareness levels. Furthermore, resilience is negatively correlated with unemployment rates, particularly in southern regions where higher unemployment aligns with reduced resilience. These findings highlight the need for targeted and equitable wildfire management strategies to improve the adaptive capacity of WUI communities.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102333"},"PeriodicalIF":8.3,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144748887","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

Mapping priority zones for urban heat mitigation in Shanghai: Heat risk vs. shelter provision 绘制上海城市热缓解优先区域：热风险与住房供应

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-07-26 DOI: 10.1016/j.compenvurbsys.2025.102330

Wenqi Qian , Fujie Rao , Xiaoyu Li , Dayi Lai

Global climate change has intensified heat wave events, raising their intensity, duration, and frequency. Outdoor urban green spaces and indoor air-conditioned spaces serve as critical ‘heat shelters’, providing crucial cooling relief to extreme heat. However, there is a lack of studies focused on the spatial distribution of potential heat shelters and how shelters in different urban areas match varying degrees of heat risk. To address this research gap, we quantify and map heat risks and shelter provisions of administrative neighborhoods (often the smallest level of urban governance) and walkable grids of 500 × 500 m (a commonly-used comfortable walking distance for vulnerable groups such as the elderly people), and identify vulnerable areas where heat mitigation interventions should be prioritized. We select Shanghai – a metropolis of around 25 million people experiencing increasingly extreme heat wave events - for the case study. We measure heat risk by a composite index incorporating heat hazard, exposure and vulnerability. We largely measure heat provision by the number of indoor air-conditioned venues and outdoor green spaces, weighted by their time availability. Our findings reveal a general decrease in heat mitigation priority levels from the urban core to the suburbs, a pattern that is consistent between neighborhoods and grids at the metropolitan scale. This said, at smaller scales, significant differences between these two types of spatial units emerged in the degree and distribution of heat mitigation priority levels, revealing nuanced, inequitable capacities of different urban areas to tackle extreme heat. Our study provides a novel and systematic lens for assessing heat mitigation priority levels, informing more effective strategies for planning and managing heat shelters and allocating heat mitigation resources.

全球气候变化加剧了热浪事件，增加了它们的强度、持续时间和频率。室外城市绿地和室内空调空间作为关键的“热庇护所”，为极端高温提供关键的冷却缓解。然而，缺乏对潜在热避难所的空间分布以及不同城市地区的避难所如何匹配不同程度的热风险的研究。为了解决这一研究差距，我们量化并绘制了行政街区（通常是城市治理的最小层面）和500 × 500米（老年人等弱势群体常用的舒适步行距离）的步行网格的热风险和住所供应图，并确定了应优先采取热缓解干预措施的脆弱区域。我们选择了拥有2500万人口的大都市上海作为案例研究对象，上海正在经历越来越多的极端热浪事件。我们通过结合热危害、暴露和脆弱性的综合指数来衡量热风险。我们主要通过室内空调场地和室外绿地的数量来衡量热量供应，并根据它们的可用性进行加权。我们的研究结果揭示了从城市核心到郊区的热缓解优先级普遍下降，这种模式在大都市尺度上在社区和网格之间是一致的。也就是说，在较小的尺度上，这两种类型的空间单元在热缓解优先级的程度和分布上出现了显著差异，揭示了不同城市地区应对极端高温的细微差别和不公平能力。我们的研究为评估热减排优先级提供了一种新颖而系统的视角，为规划和管理热庇护所以及分配热减排资源提供了更有效的策略。

{"title":"Mapping priority zones for urban heat mitigation in Shanghai: Heat risk vs. shelter provision","authors":"Wenqi Qian , Fujie Rao , Xiaoyu Li , Dayi Lai","doi":"10.1016/j.compenvurbsys.2025.102330","DOIUrl":"10.1016/j.compenvurbsys.2025.102330","url":null,"abstract":"<div><div>Global climate change has intensified heat wave events, raising their intensity, duration, and frequency. Outdoor urban green spaces and indoor air-conditioned spaces serve as critical ‘heat shelters’, providing crucial cooling relief to extreme heat. However, there is a lack of studies focused on the spatial distribution of potential heat shelters and how shelters in different urban areas match varying degrees of heat risk. To address this research gap, we quantify and map heat risks and shelter provisions of administrative neighborhoods (often the smallest level of urban governance) and walkable grids of 500 × 500 m (a commonly-used comfortable walking distance for vulnerable groups such as the elderly people), and identify vulnerable areas where heat mitigation interventions should be prioritized. We select Shanghai – a metropolis of around 25 million people experiencing increasingly extreme heat wave events - for the case study. We measure heat risk by a composite index incorporating heat hazard, exposure and vulnerability. We largely measure heat provision by the number of indoor air-conditioned venues and outdoor green spaces, weighted by their time availability. Our findings reveal a general decrease in heat mitigation priority levels from the urban core to the suburbs, a pattern that is consistent between neighborhoods and grids at the metropolitan scale. This said, at smaller scales, significant differences between these two types of spatial units emerged in the degree and distribution of heat mitigation priority levels, revealing nuanced, inequitable capacities of different urban areas to tackle extreme heat. Our study provides a novel and systematic lens for assessing heat mitigation priority levels, informing more effective strategies for planning and managing heat shelters and allocating heat mitigation resources.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102330"},"PeriodicalIF":7.1,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704836","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

An agent-based model for estimating daily face-to-face contact networks in large urban systems 基于智能体的大型城市系统日常面对面接触网络估计模型

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-07-17 DOI: 10.1016/j.compenvurbsys.2025.102321

Ismaïl Saadi , Etienne Côme , Liem Binh Luong Nguyen , Mahdi Zargayouna

Detailed contact data is important to model disease transmission in dense urban areas, as human mobility and social interactions significantly impact spread. However, linking mobility, activities, and social contacts in large cities is challenging. Current models often rely on contact surveys and overlook travel behaviors. Here we present a novel modeling framework for estimating large-scale, multi-setting contact networks by leveraging high-resolution synthetic activity-travel data. Our approach introduces a new mathematical formalism to construct multi-setting contact networks from spatiotemporal co-location patterns, enabling constraints based on key statistics (e.g., contact rates per setting, proportions of each contact type), incorporation of location types, and individual activity purposes. Efficient algorithms extract co-presence events, generating validated, individual-based contact networks, from which age-specific contact matrices are derived. The approach is tested using EQASIM, an open and reproducible activity-based travel demand model that relies on publicly available data for France’s Île-de-France region. We also evaluated the spatial effects of work-from-home policies on contact patterns by modifying individuals’ activity-travel diaries. Results show that multi-setting contact networks — representing 12 million individuals distributed across 1,714,920 unique locations — can be generated in minutes while accurately reproducing setting- and age-specific spatial contact patterns.

详细的接触数据对于在人口密集的城市地区建立疾病传播模型非常重要，因为人类的流动性和社会互动会对传播产生重大影响。然而，将大城市的流动性、活动和社会联系联系起来是一项挑战。目前的模型往往依赖于接触调查，而忽略了旅行行为。在这里，我们提出了一个新的建模框架，通过利用高分辨率的综合活动-旅行数据来估计大规模的、多设置的接触网络。我们的方法引入了一种新的数学形式，从时空共定位模式构建多设置接触网络，实现基于关键统计数据（例如，每个设置的接触率，每种接触类型的比例）的约束，结合位置类型和个人活动目的。有效的算法提取共同存在事件，生成经过验证的、基于个体的接触网络，并从中派生出特定年龄的接触矩阵。该方法使用EQASIM进行了测试，EQASIM是一个开放的、可重复的基于活动的旅行需求模型，它依赖于法国Île-de-France地区的公开数据。我们还通过修改个人的活动-旅行日记来评估在家工作政策对接触模式的空间效应。结果表明，在几分钟内就可以生成分布在1,714,920个不同地点的1200万人的多环境接触网络，同时准确地再现了特定环境和年龄的空间接触模式。

{"title":"An agent-based model for estimating daily face-to-face contact networks in large urban systems","authors":"Ismaïl Saadi , Etienne Côme , Liem Binh Luong Nguyen , Mahdi Zargayouna","doi":"10.1016/j.compenvurbsys.2025.102321","DOIUrl":"10.1016/j.compenvurbsys.2025.102321","url":null,"abstract":"<div><div>Detailed contact data is important to model disease transmission in dense urban areas, as human mobility and social interactions significantly impact spread. However, linking mobility, activities, and social contacts in large cities is challenging. Current models often rely on contact surveys and overlook travel behaviors. Here we present a novel modeling framework for estimating large-scale, multi-setting contact networks by leveraging high-resolution synthetic activity-travel data. Our approach introduces a new mathematical formalism to construct multi-setting contact networks from spatiotemporal co-location patterns, enabling constraints based on key statistics (e.g., contact rates per setting, proportions of each contact type), incorporation of location types, and individual activity purposes. Efficient algorithms extract co-presence events, generating validated, individual-based contact networks, from which age-specific contact matrices are derived. The approach is tested using EQASIM, an open and reproducible activity-based travel demand model that relies on publicly available data for France’s Île-de-France region. We also evaluated the spatial effects of work-from-home policies on contact patterns by modifying individuals’ activity-travel diaries. Results show that multi-setting contact networks — representing 12 million individuals distributed across 1,714,920 unique locations — can be generated in minutes while accurately reproducing setting- and age-specific spatial contact patterns.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102321"},"PeriodicalIF":7.1,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653395","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

Modeling spatial and temporal urban environmental noise using street view imagery and machine learning 利用街景图像和机器学习建模时空城市环境噪声

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-07-11 DOI: 10.1016/j.compenvurbsys.2025.102327

Devin Yongzhao Wu , Jue Wang

This study proposes a framework for modeling environmental noise pollution by integrating land use regression (LUR) with machine learning models and street built environments. Using noise data collected from 128 locations over nine consecutive days in Mississauga, Ontario, Canada, the research demonstrates that incorporating finer-scale street built environment features derived from street view images significantly improves noise prediction accuracy. The model using XGBoost and street view-derived variables significantly outperforms traditional LUR-based models. The results indicate that street-level characteristics, particularly terrain, play a critical role in modeling noise levels, complementing traditional land use and NDVI-based greenness. Furthermore, the research highlights the importance of using non-linear models like XGBoost to capture complex relationships between noise and urban features. This approach offers valuable insights for advancing environmental noise modeling, which further supports future public health studies investigating the impact of noise exposure on population health.

本研究提出了一个将土地利用回归（LUR）与机器学习模型和街道建筑环境相结合的环境噪声污染建模框架。通过对加拿大安大略省密西沙加市128个地点连续9天收集的噪声数据进行分析，研究表明，结合来自街景图像的更精细尺度的街道建筑环境特征，可以显著提高噪声预测的准确性。使用XGBoost和街景衍生变量的模型明显优于传统的基于lur的模型。结果表明，街道水平特征，特别是地形，在模拟噪声水平方面起着关键作用，补充了传统的土地利用和基于ndvi的绿化。此外，该研究强调了使用像XGBoost这样的非线性模型来捕捉噪音和城市特征之间复杂关系的重要性。该方法为推进环境噪声建模提供了有价值的见解，进一步支持未来调查噪声暴露对人口健康影响的公共卫生研究。

{"title":"Modeling spatial and temporal urban environmental noise using street view imagery and machine learning","authors":"Devin Yongzhao Wu , Jue Wang","doi":"10.1016/j.compenvurbsys.2025.102327","DOIUrl":"10.1016/j.compenvurbsys.2025.102327","url":null,"abstract":"<div><div>This study proposes a framework for modeling environmental noise pollution by integrating land use regression (LUR) with machine learning models and street built environments. Using noise data collected from 128 locations over nine consecutive days in Mississauga, Ontario, Canada, the research demonstrates that incorporating finer-scale street built environment features derived from street view images significantly improves noise prediction accuracy. The model using XGBoost and street view-derived variables significantly outperforms traditional LUR-based models. The results indicate that street-level characteristics, particularly terrain, play a critical role in modeling noise levels, complementing traditional land use and NDVI-based greenness. Furthermore, the research highlights the importance of using non-linear models like XGBoost to capture complex relationships between noise and urban features. This approach offers valuable insights for advancing environmental noise modeling, which further supports future public health studies investigating the impact of noise exposure on population health.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102327"},"PeriodicalIF":7.1,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144595513","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

Housing segregation in Chinese major cities: A K-nearest neighbor analysis of longitudinal big data 中国主要城市的住房隔离：纵向大数据的k近邻分析

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-07-01 DOI: 10.1016/j.compenvurbsys.2025.102326

Sebastian Kohl , Bo Li , Can Cui

Most studies on residential segregation in China have primarily relied on decennial population census data, which lacks the granularity and timeliness needed to capture segregation dynamics with higher frequency. Drawing on georeferenced housing market transaction data between 2012 and 2023 in Shanghai and Beijing, and employing fine-grained spatial segregation analysis techniques, including k-nearest neighbor approaches (k−NN) and modifiable grids, we find that housing segregation by price and size increased between 2012 and 2018, followed by a decline thereafter, particularly in the larger-sized and higher-priced market segments. While segregation levels are generally comparable between the two cities, Shanghai exhibits higher segregation for the top 20 % of apartments, while Beijing shows greater segregation for the bottom 20 %. Segregation is highest for prices, followed by rents, with housing size showing the lowest segregation. Expanding the analysis to 11 major Chinese cities, we suggest that high and rising housing prices are associated with increasing segregation, particularly in cities with lower initial segregation. Methodologically, this paper demonstrates that leveraging big transaction and listing data, alongside utilizing fine-grained spatial analysis, can advance our understanding of urban inequalities.

大多数关于中国居住隔离的研究主要依赖于十年一次的人口普查数据，缺乏更高频率捕捉隔离动态所需的粒度和及时性。利用2012年至2023年上海和北京的地理参考住房市场交易数据，并采用包括k-近邻方法（k - NN）和可修改网格在内的细粒度空间隔离分析技术，我们发现，2012年至2018年期间，价格和规模的住房隔离有所增加，之后有所下降，特别是在规模较大和价格较高的细分市场。虽然两个城市的隔离程度大致相当，但上海的前20%的公寓隔离程度更高，而北京的后20%的公寓隔离程度更高。房价的隔离程度最高，其次是租金，住房面积的隔离程度最低。将分析扩展到中国11个主要城市，我们认为高房价和不断上涨的房价与日益加剧的隔离有关，特别是在最初隔离程度较低的城市。在方法上，本文表明，利用大交易和上市数据，以及利用细粒度空间分析，可以促进我们对城市不平等的理解。

{"title":"Housing segregation in Chinese major cities: A K-nearest neighbor analysis of longitudinal big data","authors":"Sebastian Kohl , Bo Li , Can Cui","doi":"10.1016/j.compenvurbsys.2025.102326","DOIUrl":"10.1016/j.compenvurbsys.2025.102326","url":null,"abstract":"<div><div>Most studies on residential segregation in China have primarily relied on decennial population census data, which lacks the granularity and timeliness needed to capture segregation dynamics with higher frequency. Drawing on georeferenced housing market transaction data between 2012 and 2023 in Shanghai and Beijing, and employing fine-grained spatial segregation analysis techniques, including k-nearest neighbor approaches (<em>k</em>−NN) and modifiable grids, we find that housing segregation by price and size increased between 2012 and 2018, followed by a decline thereafter, particularly in the larger-sized and higher-priced market segments. While segregation levels are generally comparable between the two cities, Shanghai exhibits higher segregation for the top 20 % of apartments, while Beijing shows greater segregation for the bottom 20 %. Segregation is highest for prices, followed by rents, with housing size showing the lowest segregation. Expanding the analysis to 11 major Chinese cities, we suggest that high and rising housing prices are associated with increasing segregation, particularly in cities with lower initial segregation. Methodologically, this paper demonstrates that leveraging big transaction and listing data, alongside utilizing fine-grained spatial analysis, can advance our understanding of urban inequalities.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102326"},"PeriodicalIF":7.1,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522231","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

Social areas revisited through the lens of mobility: A comparative study of the traditional and mobility approaches 通过流动性视角重新审视社会领域：传统方法与流动性方法的比较研究

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-06-29 DOI: 10.1016/j.compenvurbsys.2025.102325

Run Shi , Anthony Gar-On Yeh , Fang Bian

Social area analysis is a framework for understanding residential social structure as a product of urbanization and economic development. Building on our previous findings that socioeconomically similar residents exhibit different mobility patterns, this study examines urban socio-spatial structure by incorporating commuting patterns from mobile phone data with census in Shenzhen, China. We conduct a comparative analysis to explore differences between the traditional and mobility approaches. Principal Component Analysis (PCA) results reveal that mobility is an essential dimension of socio-spatial differentiation at the aggregated neighborhood committee level. The derived residential social structure explicitly highlights mobility disparities, providing evidence for possible segregation and potential improvements in urban planning. By analyzing the interplays of economic, political, and social forces, we conceptualize mobility as a sub-dimension of social space. The contribution of this study lies in two folds. First, we propose a framework for integrating mobile phone data with census data to capture mobility disparities at the aggregated level with the concept of activity space. Second, we explore the role of mobility in delineating urban socio-spatial structure, providing a novel perspective for examining the internal spatial structure of cities.

社会区域分析是将住宅社会结构作为城市化和经济发展的产物来理解的一个框架。基于我们之前的研究结果，社会经济相似的居民表现出不同的流动模式，本研究通过结合移动电话数据和中国深圳人口普查的通勤模式来研究城市社会空间结构。我们进行了比较分析，以探讨传统方法和流动方法之间的差异。主成分分析（PCA）结果表明，流动性是综合居委会社会空间分异的重要维度。由此衍生的住宅社会结构明确强调了流动性差异，为可能的隔离和城市规划的潜在改进提供了证据。通过分析经济、政治和社会力量的相互作用，我们将流动性概念化为社会空间的一个子维度。本研究的贡献在于两个方面。首先，我们提出了一个整合移动电话数据和人口普查数据的框架，通过活动空间的概念在总体水平上捕捉移动差异。其次，我们探讨了流动性在描述城市社会空间结构中的作用，为研究城市内部空间结构提供了一个新的视角。

{"title":"Social areas revisited through the lens of mobility: A comparative study of the traditional and mobility approaches","authors":"Run Shi , Anthony Gar-On Yeh , Fang Bian","doi":"10.1016/j.compenvurbsys.2025.102325","DOIUrl":"10.1016/j.compenvurbsys.2025.102325","url":null,"abstract":"<div><div>Social area analysis is a framework for understanding residential social structure as a product of urbanization and economic development. Building on our previous findings that socioeconomically similar residents exhibit different mobility patterns, this study examines urban socio-spatial structure by incorporating commuting patterns from mobile phone data with census in Shenzhen, China. We conduct a comparative analysis to explore differences between the traditional and mobility approaches. Principal Component Analysis (PCA) results reveal that mobility is an essential dimension of socio-spatial differentiation at the aggregated neighborhood committee level. The derived residential social structure explicitly highlights mobility disparities, providing evidence for possible segregation and potential improvements in urban planning. By analyzing the interplays of economic, political, and social forces, we conceptualize mobility as a sub-dimension of social space. The contribution of this study lies in two folds. First, we propose a framework for integrating mobile phone data with census data to capture mobility disparities at the aggregated level with the concept of activity space. Second, we explore the role of mobility in delineating urban socio-spatial structure, providing a novel perspective for examining the internal spatial structure of cities.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102325"},"PeriodicalIF":7.1,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510637","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

Enhancing transparency in land use change modeling: Leveraging eXplainable AI techniques for urban growth prediction with spatially distributed insights 提高土地利用变化建模的透明度：利用可解释的人工智能技术进行具有空间分布洞察力的城市增长预测

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-06-28 DOI: 10.1016/j.compenvurbsys.2025.102322

Zelin Wang , Tianshu Feng , Abolfazl Safikhani , Emre Tepe

Recent applications of machine learning (ML) and deep learning (DL) techniques in land-use change modeling have demonstrated significant success in capturing the intricate dynamics of land development. However, their “black-box” nature restricts their utility in various contexts, such as uncovering the underlying drivers of urban expansion. To mitigate this issue, we propose to utilize eXplainable AI (XAI) techniques in ML/DL methods, which presents a promising solution to this primary constraint. To that end, we introduce DL methods to investigate and predict the non-linear dynamics of land use changes. These methods achieved notably high accuracy scores and were more computationally viable than traditional statistical approaches. Moreover, the proposed approach employed in this study surpassed the parameter interpretation capabilities of statistical methods. More specifically, the proposed XAI approach not only highlights the average effects of features on the outcome but also elucidates the factors influencing specific decisions regarding land use changes, including the number of vacant parcels, the share of single-family parcels, and certain time-lagged neighborhood features. Such analyses provide invaluable insights for researchers, practitioners, and policymakers.

最近机器学习（ML）和深度学习（DL）技术在土地利用变化建模中的应用在捕捉土地发展的复杂动态方面取得了重大成功。然而，它们的“黑盒子”性质限制了它们在各种情况下的效用，例如揭示城市扩张的潜在驱动因素。为了缓解这个问题，我们建议在ML/DL方法中使用可解释的AI （XAI）技术，这为这个主要约束提供了一个有希望的解决方案。为此，我们引入DL方法来研究和预测土地利用变化的非线性动态。这些方法取得了显著的高准确性分数，并且比传统的统计方法更具计算可行性。此外，本研究所采用的方法超越了统计方法的参数解释能力。更具体地说，提出的XAI方法不仅强调了特征对结果的平均影响，而且阐明了影响土地利用变化的具体决策的因素，包括空置地块的数量、单户地块的份额和某些时间滞后的社区特征。这些分析为研究人员、从业者和政策制定者提供了宝贵的见解。

{"title":"Enhancing transparency in land use change modeling: Leveraging eXplainable AI techniques for urban growth prediction with spatially distributed insights","authors":"Zelin Wang , Tianshu Feng , Abolfazl Safikhani , Emre Tepe","doi":"10.1016/j.compenvurbsys.2025.102322","DOIUrl":"10.1016/j.compenvurbsys.2025.102322","url":null,"abstract":"<div><div>Recent applications of machine learning (ML) and deep learning (DL) techniques in land-use change modeling have demonstrated significant success in capturing the intricate dynamics of land development. However, their “black-box” nature restricts their utility in various contexts, such as uncovering the underlying drivers of urban expansion. To mitigate this issue, we propose to utilize eXplainable AI (XAI) techniques in ML/DL methods, which presents a promising solution to this primary constraint. To that end, we introduce DL methods to investigate and predict the non-linear dynamics of land use changes. These methods achieved notably high accuracy scores and were more computationally viable than traditional statistical approaches. Moreover, the proposed approach employed in this study surpassed the parameter interpretation capabilities of statistical methods. More specifically, the proposed XAI approach not only highlights the average effects of features on the outcome but also elucidates the factors influencing specific decisions regarding land use changes, including the number of vacant parcels, the share of single-family parcels, and certain time-lagged neighborhood features. Such analyses provide invaluable insights for researchers, practitioners, and policymakers.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102322"},"PeriodicalIF":7.1,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502242","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

Mapping multidimensional energy deprivation: Socio-spatial inequalities and policy implications in Great Britain 映射多维能源剥夺：社会空间不平等和政策影响在英国

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems

Pub Date : 2025-06-28 DOI: 10.1016/j.compenvurbsys.2025.102324

Meixu Chen , Caitlin Robinson , Alex Singleton

This work provides a thorough Energy Deprivation Segmentation (EDS) for Great Britain, which aims to address the complex and varied aspects of energy poverty in different small regions. By proposing a reproducible analytical framework, we combine many data sources to provide a comprehensive segmentation that encompasses various dimensions such as energy efficiency, accessibility, demand and supply, housing conditions, and financial vulnerability. The results indicate notable disparities in energy deprivation based on social and spatial factors. We observed higher degrees of deprivation in the peripheral areas of major cities and suburbs in the northern regions of England, southern regions of Wales, and central regions of Scotland. The created EDS identifies six top-level Supergroups and 14 finer Groups and was validated internally and externally to confirm its robustness and applicability. This segmentation offers a more comprehensive insights into the characteristics and distribution of energy-deprived neighbourhoods than traditional measures. This research facilitates policymakers to design targeted strategies and resource allocation to combat specific vulnerabilities within communities and foster sustainable and equitable urban growth. Additionally, a practical tool is provided for monitoring and evaluating the effectiveness of policies aimed at reducing energy poverty.

这项工作为英国提供了一个彻底的能源剥夺分割（EDS），旨在解决不同小地区能源贫困的复杂和不同方面。通过提出一个可重复的分析框架，我们结合了许多数据源，提供了一个全面的细分，包括能源效率、可及性、需求和供应、住房条件和金融脆弱性等各个方面。结果表明，基于社会和空间因素的能量剥夺存在显著差异。我们观察到，在英格兰北部地区、威尔士南部地区和苏格兰中部地区的主要城市和郊区的外围地区，贫困程度更高。创建的EDS识别了6个顶级超组和14个精细组，并进行了内部和外部验证，以确认其稳健性和适用性。与传统方法相比，这种细分方法可以更全面地了解能源匮乏社区的特征和分布。这项研究有助于决策者设计有针对性的战略和资源分配，以应对社区内的特定脆弱性，促进可持续和公平的城市增长。此外，还提供了一个实用的工具来监测和评价旨在减少能源贫穷的政策的效力。

{"title":"Mapping multidimensional energy deprivation: Socio-spatial inequalities and policy implications in Great Britain","authors":"Meixu Chen , Caitlin Robinson , Alex Singleton","doi":"10.1016/j.compenvurbsys.2025.102324","DOIUrl":"10.1016/j.compenvurbsys.2025.102324","url":null,"abstract":"<div><div>This work provides a thorough Energy Deprivation Segmentation (EDS) for Great Britain, which aims to address the complex and varied aspects of energy poverty in different small regions. By proposing a reproducible analytical framework, we combine many data sources to provide a comprehensive segmentation that encompasses various dimensions such as energy efficiency, accessibility, demand and supply, housing conditions, and financial vulnerability. The results indicate notable disparities in energy deprivation based on social and spatial factors. We observed higher degrees of deprivation in the peripheral areas of major cities and suburbs in the northern regions of England, southern regions of Wales, and central regions of Scotland. The created EDS identifies six top-level Supergroups and 14 finer Groups and was validated internally and externally to confirm its robustness and applicability. This segmentation offers a more comprehensive insights into the characteristics and distribution of energy-deprived neighbourhoods than traditional measures. This research facilitates policymakers to design targeted strategies and resource allocation to combat specific vulnerabilities within communities and foster sustainable and equitable urban growth. Additionally, a practical tool is provided for monitoring and evaluating the effectiveness of policies aimed at reducing energy poverty.</div></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"121 ","pages":"Article 102324"},"PeriodicalIF":7.1,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502243","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