本次给大家整理的是《Computers, Environment and Urban Systems》杂志2024年12月第114期的论文的题目和摘要，一共包括16篇SCI论文！
-----------关注公众号----------
![]()
Post-disaster recovery policy assessment of urban socio-physical systems
城市社会物理系统的灾后恢复政策评估
【摘要】
The post-disaster recovery system is composed of the complex interplay between physical and social infrastructures. Despite the rise of coupled physical and social post-disaster recovery systems, less attention has been paid to the interdependent role of social support ties and physical infrastructure. This paper analyzes the data-driven models of post-disaster recovery system dynamics with the interdependence between the social and physical coupling to assess the post-disaster recovery policies. This paper utilizes the large-scale mobile phone location data, power outages, and socio-economic attributes for modeling the recovery dynamics during Hurricane Harvey in 2017. Parameter estimation results show that the model has regional heterogeneity and disparate impacts on socio-economic attributes to the model. The model's budget allocation scenarios also demonstrate that different budget allocation strategies affect the recovery period. The proposed model emphasizes the complex properties of the post-disaster recovery system and the importance of heterogeneous recovery policies across regions.
【摘要翻译】
灾后恢复系统是由物理和社会基础设施之间复杂的相互作用构成的（Post-disaster recovery system）。尽管耦合的物理和社会灾后恢复系统日益受到关注，但对社会支持网络与物理基础设施相互依赖作用的关注却相对较少。本文分析了基于数据驱动的灾后恢复系统动态模型，该模型考虑了社会与物理之间的相互依赖性，以评估灾后恢复政策。本文利用2017年飓风哈维（Hurricane Harvey）期间的大规模手机定位数据、停电情况以及社会经济属性来模拟恢复动态。参数估计结果表明，模型具有区域异质性，并且对社会经济属性的影响各不相同。模型的预算分配方案也表明，不同的预算分配策略会影响恢复期。提出的模型强调了灾后恢复系统的复杂属性以及跨区域异质性恢复政策的重要性。
Unraveling changes of spending behavior in pandemic cities: A nationwide study of South Korea
解析疫情城市消费行为的变化：韩国全国范围内的研究
【摘要】
The COVID-19 pandemic, unprecedented in scale and impact, has significantly influenced consumer spending. This study leverages a longitudinal transaction dataset from South Korea to analyze how the pandemic, social distancing policies, and pandemic-related search interest have shaped spending within and across cities. We examine transaction volume and expenditure amount as city-level indicators of activity intensity and consumption demand across four stages of the early pandemic. The study finds that: (1) Social distancing caused reductions in both residents' and travelers' spending. The increase in search interest coincided with a rise in residents' spending but a decline in travelers' spending; (2) Resident transactions experienced a moderate and persistent decline across all stages, while expenditure rebounded after the 1st national outbreak. Traveler transactions and expenditure showed similar trends, with declines during outbreaks and recoveries during stable periods; (3) Disparities across cities were associated with proximity to outbreak centers and socioeconomic attributes. Cities with larger populations or those closer to epicenters experienced greater reductions in spending, while less densely populated cities saw increased traveler spending during the 2nd stable period; (4) Travelers' spending from distant cities significantly decreased during the 1st outbreak but gradually recovered as the pandemic continued, indicating evolving behavior and adaptation; (5) Changes across spending categories exhibited significant heterogeneity. Residents showed increased demand for essential goods and online shopping, while recreation-related industries struggled throughout. These findings highlight the characteristics and disparities among consumers, cities, and industries, providing information for policymakers to formulate tailored support programs for industries experiencing increased demand or significant impacts. This study emphasizes the need to develop robust strategies for crisis management and economic resilience to mitigate the impacts of future health crises.
COVID-19对消费者支出行为产生了显著影响。本研究利用韩国的纵向交易数据集（longitudinal transaction dataset），分析了全球性流行病、社交距离政策（和与全球性流行病相关的搜索兴趣如何塑造城市内部及城市间的消费行为。研究发现：
社交距离政策导致居民和旅行者的支出减少。搜索兴趣的增加与居民支出的增加同时发生，但旅行者支出却下降；
居民交易在所有阶段都经历了适度且持续的下降，而支出在第一次全国性爆发后有所反弹。旅行者的交易和支出显示了类似的趋势，在爆发期间下降，在稳定期间恢复；
城市间的差异与疫情中心的接近程度和社会经济属性有关。人口较多的城市或那些靠近疫情中心的城市支出减少更多，而人口密度较低的城市在第二次稳定期间旅行者支出增加。
这些发现突出了消费者、城市和行业之间的特点和差异，为政策制定者提供了信息，以制定针对需求增加或受到重大影响的行业量身定制的支持计划。本研究强调了制定强大的危机管理和经济恢复策略的必要性，以减轻未来健康危机的影响。
PRIME: A CyberGIS Platform for Resilience Inference Measurement and Enhancement
PRIME：一个用于韧性推断测量和增强的CyberGIS平台
【摘要】
In an era of increased climatic disasters, there is an urgent need to develop reliable frameworks and tools for evaluating and improving community resilience to climatic hazards at multiple geographical and temporal scales. Defining and quantifying resilience in the social domain is relatively subjective due to the intricate interplay of socioeconomic factors with disaster resilience. To broaden upon it, the choice of indicators and their subsequent ranking for the aggregation into an index is subjective in nature. This aggregation is not empirically validated and is prone to omit the nuances of localized resilience changes and causal factors affecting it, while leading to oversimplified conclusions. Meanwhile, there is a lack of scientifically and computationally rigorous, user-friendly tools that can support customized resilience assessment with consideration of local conditions. This study addresses these gaps through the power of CyberGIS with three objectives: 1) To develop an empirically validated disaster resilience model - Customizable Resilience Inference Measurement (RIM), designed for multi-scale community resilience assessment and influential socioeconomic factors identification; 2) To implement a Platform for Resilience Inference Measurement and Enhancement (PRIME) module in the CyberGISX platform backed by high-performance computing, enabling users to apply and customize RIM to compute and visualize disaster resilience; 3) To demonstrate the utility of PRIME through a representative study to understand the geographical disparities of county-level community resilience to natural hazards in the United States and identifying the driving factors of resilience in the social domain. Customizable RIM generates vulnerability, adaptability, and overall resilience scores derived from empirical parameters—hazard threat, damage, and recovery. Computationally intensive Machine Learning (ML) methods are employed to explain the intricate relationships between these scores and socioeconomic driving factors. PRIME provides a web-based notebook interface guiding users to select study areas, configure parameters, calculate and geo-visualize resilience scores, and interpret socioeconomic factors shaping resilience capacities. A representative study showcases the efficiency of the platform while explaining how the visual results obtained may be interpreted. The essence of this work lies in its comprehensive architecture that encapsulates the requisite data, analytical and geo-visualization functions, and ML models for resilience assessment. This setup provides a foundation for assessing resilience and strategizing enhancement interventions.
【摘要翻译】
在气候变化灾害日益增多的时代，迫切需要开发可靠的框架和工具，以在多个地理和时间尺度上评估和提高社区对气候灾害的韧性。在社会领域定义和量化韧性相对主观，因为社会经济因素与灾害韧性之间的相互作用复杂。为了进一步探讨这一问题，选择指标及其随后的排名以聚合为一个指数是主观的。这种聚合没有经过实证验证，容易忽略本地韧性变化的细微差别和影响它的因果因素，同时导致过于简化的结论。与此同时，缺乏科学和计算上严格、用户友好的工具，这些工具可以支持考虑本地条件的定制韧性评估。本研究通过CyberGIS的力量解决这些差距，具有三个目标：1）开发一个经过实证验证的灾害韧性模型——可定制的韧性推断测量（RIM），旨在进行多尺度社区韧性评估和识别有影响力的经济社会因素；
2）在CyberGISX平台中实现一个用于韧性推断测量和增强（PRIME）模块，该模块由高性能计算支持，使用户能够应用和定制RIM来计算和可视化灾害韧性；
3）通过代表性研究展示PRIME的实用性，以了解美国县级社区对自然灾害的韧性地理差异，并识别社会领域韧性驱动因素。
可定制的RIM生成的脆弱性、适应性和总体韧性分数来源于实证参数——灾害威胁、损害和恢复。计算密集型的机器学习（ML）方法被用来解释这些分数与经济社会驱动因素之间的复杂关系。PRIME提供了一个基于网络的笔记本界面，指导用户选择研究区域、配置参数、计算和地理可视化韧性分数，并解释塑造韧性能力的经济社会因素。代表性研究展示了平台的效率，同时解释了如何解释获得的视觉结果。这项工作的本质在于其全面的架构，涵盖了进行韧性评估所需的数据、分析和地理可视化功能以及ML模型。这种设置为评估韧性和制定增强干预措施提供了基础。
A tale of many cities: Mapping social infrastructure and social capital across the United States
多城故事：在美国范围内绘制社会基础设施和社会资本
【摘要】
Research has underscored the role that social infrastructure - the places and spaces that help build and maintain social ties - plays in improving quality of life, lowering crime, and creating connection. Little work to date has shown how, across multiple urban environments, these parks, community centers, cafes, mosques, libraries, and other facilities correlate with bonding, bridging, and linking social capital. Our paper seeks to better understand the relationship between social infrastructure and bonding, bridging, and linking social capital along with inter-city differences in social facilities. We use Google map data from 25 urban centers in North America along with information from census-tract level Social Capital Index (SoCI) scores to map out these connections. We find that, controlling for other factors, social infrastructure positively correlates with bridging social capital - the weak or thin ties that build heterogeneous groups. As intended, many forms of social infrastructure help people engage with broader and more diverse networks, that is, provide a structure for connective democracy. Further, some cities' residents have extensive access to social infrastructure - such as those of Washington DC - while in others, such as Los Angeles, have far less. These findings bring with them policy recommendations for communities, NGOs, and decision makers alike.
【摘要翻译】
研究强调了社会基础设施——帮助建立和维护社会联系的场所和空间——在提高生活质量、降低犯罪率和创造联系方面的作用。迄今为止，很少有研究展示了这些公园、社区中心、咖啡馆、清真寺、图书馆和其他设施如何在多个城市环境中与社会凝聚力、桥梁和链接社会资本相关联。我们的论文旨在更好地理解社会基础设施与社会凝聚力、桥梁和链接社会资本之间的关系，以及城市间社会设施的差异。我们使用来自北美25个中心城市的数据，结合来自人口普查区级社会资本指数（Social Capital Index，SoCI）分数的信息，来绘制这些联系。我们发现，在控制其他因素的情况下，社会基础设施与桥梁社会资本呈正相关——桥梁社会资本是指构建异质群体的弱或薄的社会联系。正如预期的那样，许多形式的社会基础设施帮助人们与更广泛和更多样化的网络互动，即为连接民主提供了结构。此外，一些城市的居民对社会基础设施有广泛的接触——例如华盛顿特区的居民——而在其他城市，如洛杉矶，接触则少得多。这些发现为社区、非政府组织和决策者带来了政策建议。
Strategic allocation of landmarks to reduce uncertainty in indoor navigation
战略分配地标以减少室内导航的不确定性
【摘要】
Indoor navigation systems often rely on verbal, turn-based route instructions. These can, at times, be ambiguous at complex decision points with multiple paths intersecting under angles that are not well distinguished by theturn grammar used. Landmarks can be included into turn instructions to reduce this ambiguity. Here, we propose an approach to optimize landmark allocation to improve the clarity of route instructions. This study assumes that landmark locations are constrained to a pre-determined set of slots. We select a minimum-size subset of the set of all slots and allocate it with landmarks, such that the navigation ambiguity is resolved. Our methodology leverages computational geometric analysis, graph algorithms, and optimization formulations to strategically incorporate landmarks into indoor route instructions. We propose a method to optimize landmark allocation in indoor navigation guidance systems, improving the clarity of route instructions at complex decision points that are inadequately served by turn-based instructions alone.
室内导航系统通常依赖于口头的、基于转弯的路线指令。在复杂决策点，这些指令有时可能因多条路径在角度上不明显区分而变得含糊不清，尤其是在使用转弯语法时。可以通过将地标纳入转弯指令中来减少这种歧义。在这里，我们提出了一种优化地标分配的方法，以提高路线指令的清晰度。本研究假设地标位置受限于一组预定义的插槽。我们从所有插槽的集合中选择一个最小尺寸的子集，并将其分配地标，以解决导航歧义。我们的方法利用计算几何分析、图算法和优化公式，将地标策略性地纳入室内路线指令中。我们提出了一种优化室内导航指导系统中地标分配的方法，改善了仅由基于转弯的指令无法充分服务的复杂决策点的路线指令的清晰度。
A specialized inclusive road dataset with elevation profiles for realistic pedestrian navigation using open geospatial data and deep learning
使用开放的地理空间数据和深度学习为现实中的行人导航提供具有高程剖面的专业包容性道路数据
【摘要】
Built environment characteristics can greatly influence pedestrians' route choices with factors beyond distance, such as accessibility, convenience, safety, and aesthetics, playing crucial roles. Although current navigation apps, such as Google Maps and Waze, have successfully provided driving directions, their navigation services are insufficient and sometimes unrealistic for addressing pedestrians' needs, largely due to the lack of dedicated pedestrian networks and the associated navigation algorithms. To address the research gaps, this paper proposes a novel approach that integrates freely available geospatial data and computer vision technology to create a specialized inclusive network dataset for outdoor pedestrian navigation. Moreover, a pedestrian navigation algorithm is developed to generate more practical “shortest” and “alternative” paths by incorporating various sidewalk attributes. We applied the method to create a pedestrian navigation network in Las Vegas. SpaceNet's open imagery dataset was used to extract Las Vegas's road networks. A virtual audit process assessed the visual and operational properties of the sidewalk networks using Google street-level images, evaluating factors including sidewalk presence, widths, surface types and conditions, missing curb ramps, greenery, protection from weather conditions, and lighting. Google Earth's open elevation data were used to analyze road elevation profiles as meaningful 3D indicators of sidewalk accessibility for wheelchair users. Further, additional geometric properties of the network, including road curviness, proximity to road intersections, and directional changes, were detected and analyzed. A navigation experiment conducted with individuals having varying mobility abilities, including regular pedestrians, older adults, and wheelchair users demonstrated the effectiveness of the newly developed network and algorithm in meeting the diverse needs of pedestrians.
【摘要翻译】
建成环境的特征可以极大地影响行人的路线选择，除了距离之外，可达性、便利性、安全性和美观性等因素也起着关键作用。尽管当前的导航应用，如谷歌地图（Google Maps）和瓦兹（Waze），已成功提供了驾车方向，但它们的导航服务对于满足行人的需求来说是不足且有时不现实的，这主要是由于缺乏专门的行人网络和相关的导航算法。为了解决研究差距，本文提出了一种新方法，整合了自由可用的地理空间数据和计算机视觉技术，创建了一个专门化的包容性网络数据集，用于户外行人导航。此外，开发了一个行人导航算法，通过纳入各种人行道属性，生成更实用的“最短”和“替代”路径。我们将该方法应用于在拉斯维加斯创建行人导航网络。使用SpaceNet的开放图像数据集提取了拉斯维加斯的道路网络。一个虚拟审计过程使用谷歌街景图像评估了人行道网络的视觉和操作属性，评估了包括人行道存在、宽度、表面类型和状况、缺失的路缘坡道、绿化、抵御天气条件和照明等因素。使用谷歌地球（Google Earth）的开放高程数据来分析道路高程剖面，作为轮椅用户人行道可达性的有意义的3D指标。此外，还检测并分析了网络的其他几何属性，包括道路弯曲度、接近道路交叉口的距离和方向变化。与具有不同移动能力的个体进行的导航实验，包括普通行人、老年人和轮椅用户，证明了新开发的网络和算法在满足行人的多样化需求方面的有效性。
Unraveling nonlinear and spatial non-stationary effects of urban form on surface urban heat islands using explainable spatial machine learning
使用可解释的空间机器学习解析城市形态对地表城市热岛效应的非线性和空间非平稳影响
【摘要】
Under global warming, surface urban heat islands (SUHI) threaten human health and urban ecosystems. However, scant research focused on exploring the complex associations between urban form factors and SUHI at the county scale, compared with rich studies at the city scale. Therefore, this study simultaneously examined the nonlinear and spatial non-stationary association between SUHI and urban form factors (e.g., landscape structure, built environment, and industrial pattern) across 2321 Chinese counties. An explainable spatial machine learning method, combining the Geographically Weighted Regression, Random Forest, and Shapley Additive Explanation model, was employed to deal with nonlinearity, spatial non-stationary, and interpretability of modeling. The results indicate the remarkable spatial disparities in the relationship between urban form factors and SUHI. Landscape structure contributes the most in southern counties, while the built environment is more important in northeastern counties. The impact of building density and building height increases with the county size and becomes the main driver of urban heat in mega counties. Most urban form factors exhibit nonlinear impacts on SUHI. For example, urban contiguity significantly affects SUHI beyond a threshold of 0.93, while building density does so at 0.17. By comparison, the influence of shape complexity remains stable above a value of 7. Factors such as industrial density and diversity have a varied influence on SUHI between daytime and nighttime. The results of local explanations and nonlinear effects provide targeted regional mitigation strategies for urban heat.
【摘要翻译】
在全球变暖的背景下，地表城市热岛（Surface Urban Heat Islands，简称SUHI）对人类健康和城市生态系统构成威胁。然而，与城市尺度的丰富研究相比，很少有研究关注在县级尺度上探索城市形态因素与SUHI之间的复杂关联。因此，本研究同时检验了SUHI与城市形态因素（例如景观结构、建成环境和工业模式）在中国2321个县之间的非线性和空间非平稳关联。本研究采用了一种可解释的空间机器学习方法，结合地理加权回归（Geographically Weighted Regression）、随机森林（Random Forest）和夏普利加性解释模型（Shapley Additive Explanation model），以处理模型的非线性、空间非平稳性和可解释性。结果表明，城市形态因素与SUHI之间的关系存在显著的空间差异。景观结构在南部县的贡献最大，而建成环境在东北部县更为重要。建筑密度和建筑高度的影响随着县的规模增大而增加，并成为特大型县城市热的主要驱动因素。大多数城市形态因素对SUHI的影响是非线性的。例如，城市连通性在阈值0.93以上显著影响SUHI，而建筑密度在0.17以上如此。相比之下，形状复杂性的影响力在7以上的值保持稳定。工业密度和多样性等因素在白天和夜间对SUHI的影响各不相同。局部解释和非线性效应的结果为城市热的针对性区域缓解策略提供了依据。
A graph-based modelling approach for the representation and analysis of urban conflicts
基于图的建模方法用于城市冲突的表示和分析
【摘要】
The many human interactions within cities inevitably generate relations between different places, civic and political organisations, authorities, and eventually conflictual events. Among all conflicts occurring in urban environments, if some are isolated events, many are connected by strong dependencies that generate networks in space and time. The research presented in this paper introduces a graph-based approach whose objective is to track the intertwined relations and dependencies that are associated with registered conflicts. The approach is experimented with and implemented using a combination of a graph-based database and visual graphics that together provide a series of data query capabilities and analysis specifically adapted to the context of our study. An experimental application to a series of conflicts reported in local media from 1985 to 2007 in the urban area of Montréal in Canada is presented and discussed.
【摘要翻译】
城市中众多的人际互动不可避免地在不同地点、公民和政治组织、当局之间产生关系，最终导致冲突事件的发生。在所有发生在城市环境中的冲突中，虽然一些是孤立事件，但许多冲突之间存在强依赖关系，这些关系在时间和空间上形成网络。本文所呈现的研究介绍了一种基于图的方法，其目标是追踪与已登记冲突相关的错综关系和依赖关系。该方法通过结合图数据库和可视化图形进行实验和实施，这两者共同提供了一系列特定于我们研究背景的数据查询能力和分析。文中还介绍并讨论了对1985年至2007年间在加拿大蒙特利尔城市地区当地媒体报道的一系列冲突的实验应用。
Inclusive accessibility: Analyzing socio-economic disparities in perceived accessibility
包容性可达性：分析感知可达性中的社会经济差异
【摘要】
Existing accessibility measures mainly focus on the physical limitations of travel and ignore travelers' perceptions, behavior, and socio-economic differences. By integrating approaches in time geography and travel behavior, this study introduces a bottom-up inclusive accessibility concept that aggregates individual-level travel perceptions across socio-economic groups to evaluate their multimodal access to opportunities. We classify accessibility constraints into hard constraints (physical space-time limitations to travel) and soft constraints (perceptual factors influencing travel, such as safety perceptions, comfort, and willingness to travel). We categorize travelers into 12 mutually exclusive socio-economic groups from a mobility survey dataset of 477 travelers. We apply a support vector regressor-based ensemble algorithm to estimate network-level walking perception scores as soft constraints for each social group. We derive group-specific inclusive accessibility measures that consider space-time limitations from transit and sidewalk networks as hard constraints and minimize the group-specific soft constraint to a certain threshold. Finally, we demonstrate the effectiveness of group-specific inclusive accessibility by comparing it with the classic access measure. Our study provides scientific evidence on how people of varying socio-economic statuses perceive the same travel environment differently. We find that socio-economically disadvantaged communities experience higher mobility barriers and lower accessibility while walking and using transit in Columbus, OH. Our study demonstrates a transition from person- to place-based accessibility measures by sequentially quantifying mobility perceptions for individual travelers and aggregating them by social groups for a large geographic scale, making this approach suitable for equity-oriented need-specific transportation planning.
【摘要翻译】
现有的可达性测量主要关注旅行的物理限制，而忽视了旅行者的感知、行为和社会经济差异。通过整合时间地理学和旅行行为的方法，本研究引入了一个自下而上的包容性可达性概念，该概念将跨社会经济群体的个体级旅行感知聚合起来，以评估他们对机会的多模式可达性。我们将可达性限制分为硬限制（旅行的物理时空限制）和软限制（影响旅行的感知因素，如安全感知、舒适度和旅行意愿）。我们从477名旅行者的移动性调查数据集中将旅行者分类为12个互斥的社会经济群体。我们应用基于支持向量回归器的集成算法来估计每个社会群体的网络级步行感知分数作为软限制。我们推导出特定于群体的包容性可达性度量，这些度量考虑了从公共交通和人行道网络中获得的时空限制作为硬限制，并将特定于群体的软限制最小化到一定阈值。最后，我们通过将其与经典的可达性度量进行比较，展示了特定于群体的包容性可达性的有效性。我们的研究提供了科学证据，说明不同社会经济地位的人如何以不同的方式感知相同的旅行环境。我们发现，在俄亥俄州哥伦布市，社会经济地位较低的社区在步行和使用公共交通时面临更高的流动性障碍和较低的可达性。我们的研究展示了从以个人为中心到以地点为中心的可达性度量的转变，通过依次量化个别旅行者的流动性感知，并按社会群体进行聚合，适用于大规模地理范围，使这种方法适合于以公平为导向的特定需求的交通规划。
Spatiotemporal dynamics of ethnoracial diversity and segregation in Los Angeles County: Insights from mobile phone data
洛杉矶县种族和民族多样性和隔离的时空动态：来自手机数据的洞见
【摘要】
Ethnoracial segregation persists as a pressing issue in American cities. Understanding these issues is crucial for promoting social equity and justice, and planning more inclusive cities. Prior research has predominantly emphasized residential ethnoracial diversity but has often overlooked or inadequately addressed ethnoracial diversity and segregation in individuals' daily activities and places they visit, due in part to data limitations. This study leverages a dynamic measure of ethnoracial diversity and dominance at the finest spatial scale, specifically at the Points of Interest (POI) level and various temporal contexts. Using one month of privacy-enhanced mobile phone location data in Los Angeles County, California, this study explores ethnoracial diversity and spatial segregation simultaneously in POI visits in LA County. Our findings confirm that individuals' daily mobility in urban areas enhances ethnoracial mixing at activity locations. Empirical results indicate that the diversity of visitors to a POI is significantly higher than the neighborhood diversity where the same POI is located. A significant positive linear relationship was found between the neighborhood diversity of POIs and the diversity of visitors. About 34% of the variance in the diversity of visitors to POIs can be explained by the neighborhood diversity of POIs. Our results also suggest significant spatial clusters of isolated/integrated areas regarding ethnoracial mixing in people's daily activity locations. Notably, the Hispanic or Latino population tends to stay in their own communities and experiences a higher level of segregation in their daily activity locations. The findings have significant implications for urban planners and policymakers to design targeted solutions and policies to promote social equity, integration, and equal access to public amenities and opportunities in urban spaces.
【摘要翻译】
种族和民族隔离仍是美国城市中一个紧迫的问题。理解这些问题对于促进社会公平和正义、规划更具包容性的城市至关重要。以往的研究主要强调了居住区的种族和民族多样性，但往往忽视或不充分解决个体日常活动和他们访问的地方的种族和民族多样性及隔离问题，这部分是由于数据限制。本研究利用动态的种族和民族多样性和主导性的度量方法，在最精细的空间尺度上，特别是在兴趣点（简称POI）级别和各种时间背景下进行研究。利用加州洛杉矶县一个月的隐私增强型手机定位数据，本研究同时探索了洛杉矶县POI访问中的种族和民族多样性和空间隔离。我们的发现证实，个体在城市地区的日流动性增强了活动地点的种族和民族混合。实证结果表明，访问POI的访客多样性显著高于同一POI所在社区的多样性。POI的社区多样性与访客多样性之间存在显著的正线性关系。POI访客多样性的方差中约有34%可以通过POI的社区多样性来解释。我们的结果还表明，在日常活动地点的种族和民族混合方面，存在显著的空间集群，这些集群是隔离/融合的。值得注意的是，西班牙裔或拉丁裔人口倾向于留在自己的社区，并在日常活动地点经历更高水平的隔离。这些发现对于城市规划者和政策制定者设计针对性的解决方案和政策以促进社会公平、融合以及在城市空间中平等获取公共便利设施和机会具有重要意义。
Machine-based understanding of noise perception in urban environments using mobility-based sensing data
基于机器的城市环境中噪声感知理解：利用基于移动性的感知数据
【摘要】
An accurate understanding of noise perception is important for urban planning, noise management and public health. However, the visual and acoustic urban landscapes are intrinsically linked: the intricate interplay between what we see and hear shapes noise perception in the urban environment. To measure this complex and mixed effect, we conducted a mobility-based survey in Hong Kong with 800 participants, recording their noise exposure, noise perception and GPS trajectories. In addition, we acquired Google Street View images associated with each GPS trajectory point and extracted the urban visual environment from them. This study used a multi-sensory framework combined with XGBoost and Shapley additive interpretation (SHAP) models to construct an interpretable classification model for noise perception. Compared to relying solely on sound pressure levels, our model exhibited significant improvements in predicting noise perception, achieving a six-classification accuracy of approximately 0.75. Our findings revealed that the most influential factors affecting noise perception are the sound pressure levels and the proportion of buildings, plants, sky, and light intensity. Further, we discovered non-linear relationships between visual factors and noise perception: an excessive number of buildings exacerbated noise annoyance and stress levels and diminished objective noise perception at the same time. On the other hand, the presence of green plants mitigated the effect of noise on stress levels, but beyond a certain threshold, it led to worsened objective noise perception and noise annoyance instead. Our study provides insight into the objective and subjective perception of noise pressure, which contributes to advancing our understanding of complex and dynamic urban environments.
【摘要翻译】
准确理解噪声感知对于城市规划、噪声管理和公共健康至关重要。然而，视觉和声学的城市景观是内在联系的：我们所看到的和听到的之间的复杂相互作用塑造了城市环境中的噪声感知。为了测量这种复杂而混合的效果，我们在香港进行了一项基于移动性的调查，有800名参与者，记录了他们的噪声暴露、噪声感知和GPS轨迹。此外，我们获取了与每个GPS轨迹点相关的谷歌街景图像，并从中提取了城市视觉环境。本研究使用了一个多感官框架，结合XGBoost和Shapley加性解释（SHAP）模型，构建了一个可解释的噪声感知分类模型。与仅依赖声压级相比，我们的模型在预测噪声感知方面取得了显著改进，六分类准确率达到了大约0.75。我们的发现揭示了影响噪声感知的最有影响力的因素是声压级和建筑物、植物、天空和光强度的比例。此外，我们发现了视觉因素与噪声感知之间的非线性关系：过多的建筑物加剧了噪声烦恼和压力水平，同时也降低了客观噪声感知。另一方面，绿色植物的存在减轻了噪声对压力水平的影响，但超过一定阈值后，它反而导致客观噪声感知和噪声烦恼的恶化。我们的研究提供了对噪声压力的客观和主观感知的洞察，这有助于推进我们对复杂和动态城市环境的理解。
From PSScience to digital planning: Steps towards an integrated research and practice agenda for digital planning
从PSScience到数字规划：迈向数字规划研究和实践综合议程的步骤
Up till now, a widely accepted definition of Digital Planning is missing. Following the Editorial, digital planning is defined as the application of digital technologies and data-driven approaches to enhance efficiency, effectiveness, and inclusivity in planning processes to improve social, economic, and environmental outcomes for a sustainable urban future. It is necessary to clarify the distinction between Digital Planning and two associated terminologies: Planning Support Systems (PSS) and Planning Support Science (PSScience). PSScience and Digital Planning (DP) are envisioned as distinctive but closely interconnected. PSScience acts as the scientific base of the foremost planning practice-oriented Digital Planning. Based on this double-sided distinction and interconnection with PSScience, the relatively new concept of Digital Planning is further elaborated upon, resulting in an integrated research and practice agenda. For both approaches, a quadruple collaboration will be needed between governmental organizations, market parties, societal organizations/individuals, and educational/research institutes.
【摘要翻译】
迄今为止，数字规划（Digital Planning）尚无一个被广泛接受的定义。按照编辑部的说法，数字规划被定义为应用数字技术和数据驱动的方法来提高规划过程的效率、效果和包容性，以改善社会、经济和环境成果，为可持续的城市未来做出贡献。有必要澄清数字规划与两个相关术语之间的区分：规划支持系统和规划支持科学。PSScience和数字规划被视为有区别但密切相关的。PSScience作为面向规划实践的数字规划的科学基础。基于与PSScience的这种双向区分和相互联系，进一步阐述了相对较新的数字规划概念，形成了一个综合的研究和实践议程。对于这两种方法，都需要政府组织、市场参与者、社会组织/个人以及教育/研究机构之间的四重合作。
Informal participation in digital planning: How can third parties use social media to shift power relations in planning?
非正式参与数字规划：第三方如何利用社交媒体改变规划中的权力关系？
【摘要】
In recent years, social media has become an influential tool for engaging various participants and facilitating inclusivity in digital planning. While many studies highlight local governments' use of social media for formal participation, limited research assesses its impact on power dynamics in informal participation. This study aims to fill the gap by identifying key features of social media that facilitate informal participation and applying Castells' four forms of network power to understand power dynamics among civil society, journalism, citizens, and governments in planning processes. It also develops a novel mixed-methods approach that combines social media scraping, social network analysis (SNA), semi-structured interviews, and field observation. This approach is applied to investigate the Enning Road regeneration project in Guangzhou as a case study. Analyzing data from China's Weibo, the study reveals network disputes across three dimensions: graph, community, and network statistics. Hyperlink-Induced Topic Search (HITS) and community detection results suggest that civil society and journalism have substantial networked power as they strategically utilize social media to promote collaboration, mobilize citizens, and foster communities. They also excise network-making power by switching online and offline networks, thereby transmitting online debate to a wide range of audiences and compelling local governments to shift planning priorities from demolitions to preservation.
【摘要翻译】
近年来，社交媒体已成为吸引各方参与者和促进数字规划中包容性的重要工具。虽然许多研究强调了地方政府在正式参与中使用社交媒体的情况，但对社交媒体对非正式参与中权力动态影响的研究却相对有限。本研究旨在填补这一空白，通过识别促进非正式参与的社交媒体的关键特征，并应用卡斯特尔斯（Castells）的四种网络权力形式来理解民间社会、新闻业、公民和政府在规划过程中的权力动态。此外，本研究还开发了一种新颖的混合方法方法，结合社交媒体抓取、社交网络分析（SNA）、半结构化访谈和现场观察。这种方法被应用于广州恩宁路复兴项目作为案例研究。通过分析中国微博的数据，研究发现网络争端涉及三个维度：图、社区和网络统计。超链接诱导主题搜索（HITS）和社区检测结果表明，民间社会和新闻业拥有相当的网络权力，因为它们策略性地利用社交媒体促进合作、动员公民和培养社区。它们还通过切换在线和离线网络来行使网络制造权力，从而将在线辩论传播给广泛的受众，并迫使地方政府将规划重点从拆迁转移到保护上。
Experiencing the future: Evaluating a new framework for the participatory co-design of healthy public spaces using immersive virtual reality
体验未来：评估一种新框架，用于利用沉浸式虚拟现实共同设计健康的公共空间
【摘要】
Urban densification is promoted for sustainable urban growth, yet it also generates concerns about negative health impacts on local citizens. Engaging local citizens in the co-design of densification projects is therefore crucial to address their needs and concerns. The use of immersive Virtual Reality (VR) technologies creates potential for advancing the participatory co-design of healthier urban spaces by allowing citizens to not only visualize but also experience the impacts of future designs or “what-if” scenarios. Theoretically grounded in an extended version of Sheppard's approach, which we call the Experiencing the Future Framework (EFF), we developed a study to create and evaluate an immersive VR application called CoHeSIVE. This application was designed to facilitate participatory co-design processes for healthy public spaces. CoHeSIVE, as the technological manifestation of our framework, was created through iterative workshops with end-user input. During the final workshop with 41 participants, both qualitative and quantitative data were collected, including user behavior and experiences with CoHeSIVE, especially regarding its experiential and interactive components. The vast majority of participants had positive experiences and recommended CoHeSIVE for participatory co-design processes. Participants felt confident in their design outcomes and found the user interface easy to use and effective for making and communicating design decisions. The most preferred design attributes were found to be many and clustered trees, several benches, large grass areas, high-rise buildings, more lampposts and the presence of a fountain, showing that the design outcomes were meaningful for the selected local context. Future enhancements of CoHeSIVE might include adding more design attributes, enhancing visual representations, adding multi-user capabilities, integrating generative AI and expanding CoHeSIVE's applicability to other contexts.
【摘要翻译】
城市密集化被推广为可持续城市增长的策略，但它也引发了对当地居民健康影响的担忧。因此，让当地居民参与密集化项目的共同设计至关重要，以解决他们的需求和担忧。沉浸式虚拟现实（VR）技术的使用为推进更健康的城市空间的参与式共同设计提供了潜力，它不仅允许居民可视化，还能体验未来设计或“假设”情景的影响。我们的理论基础是Sheppard方法的扩展版本，我们称之为“体验未来框架”（Experiencing the Future Framework，简称EFF），我们开展了一项研究，创建并评估了一个名为CoHeSIVE的沉浸式VR应用。这个应用旨在促进健康公共空间的参与式共同设计过程。CoHeSIVE作为我们框架的技术体现，是通过与最终用户的迭代工作坊创建的。在有41名参与者的最终工作坊中，我们收集了定性和定量数据，包括用户对CoHeSIVE的行为和体验，特别是关于其体验性和互动性组件。绝大多数参与者都有积极的体验，并推荐CoHeSIVE用于参与式共同设计过程。参与者对他们的设计成果感到自信，并发现用户界面易于使用，并且有效地进行和传达设计决策。最受欢迎的设计属性被发现是许多聚集的树木、几张长椅、大片草地、高层建筑、更多的路灯和喷泉的存在，表明设计成果对选定的当地环境是有意义的。CoHeSIVE未来的增强可能包括添加更多的设计属性、增强视觉表现、增加多用户能力、集成生成性人工智能，并扩大CoHeSIVE在其他环境中的应用。
Logistic facility identification from spatial time series data
从空间时间序列数据中识别物流设施
【摘要】
Vehicle telemetry data is becoming more ubiquitous with increasingly sensorised vehicles, but making sense of the vehicles' purpose remains challenging without additional context. Clustering the vehicle activity data and identifying the underlying facilities where the activities occur reveals much insight, particularly for logistics planning. Unfortunately, current research typically only looks at a single point in time. This paper contributes by matching geospatial patterns, each representing a facility where trucks perform activities over multiple periods. The contribution is a necessary first step in studying how urban freight movement and its underlying inter-firm networks of connectivity change over time. We demonstrate how to overcome three challenges. Firstly, the complexity of identifying facilities from non-regular geometric polygons. Secondly, the challenge associated with the scale of comparing more than 200,000 facilities on a month-to-month basis over a multi-year period. Finally, overcoming the computational challenge of the workflow and getting the required performance on a consumer-grade laptop. The paper evaluates various machine learning algorithms, highlighting a SVM that outperforms more popular deep learning and neural network alternatives, with a mean average accuracy of 96.9%.
【摘要翻译】
随着车辆越来越传感器化，车辆遥测数据变得越来越普遍，但在没有额外上下文的情况下，理解车辆的用途仍然是一个挑战。对车辆活动数据进行聚类，并识别活动发生的底层设施，可以揭示很多洞见，特别是对于物流规划来说。不幸的是，当前的研究通常只关注单一时间点。本文通过匹配地理空间模式，每个模式代表卡车在多个时间段内执行活动的设施，为研究城市货运流动及其底层企业间网络连接随时间的变化提供了必要的第一步。我们展示了如何克服三个挑战：首先，从非规则几何多边形中识别设施的复杂性；其次，与比较200,000多个设施的月度数据相比，跨多年时期的挑战；最后，克服工作流程的计算挑战，并在消费级笔记本电脑上获得所需的性能。本文评估了各种机器学习算法，突出了支持向量机（SVM）的性能优于更流行的深度学习和神经网络替代方案，平均准确率达到96.9%。
Satisfying transport needs with low carbon emissions: Exploring individual, social, and built environmental factors
满足交通需求同时降低碳排放：探索个体、社会和建成环境因素
【摘要】
The article studies the relationships between daily travel greenhouse gas (GHG) emissions and self-rated satisfaction with transport needs. It also investigates the conditions that satisfy one's transport needs at emission levels compatible with internationally agreed reduction targets by 2030 to keep warming below 1.5 degrees. It uses a representative geo-questionnaire survey from Poznan, a functional urban area in Poland (ca 800 thousand inhabitants), with 550 study participants answering questions used in the study. Four built environmental (BE) and accessibility measures are calculated using geospatial methods and used as predictors of low/high emission levels, low/high need satisfaction levels, and their combinations (i.e.,social-ecological quadrants), along with socio-demographic characteristics and transport-related resources, competences, and responsibilities. The relationship between transport need satisfaction and GHG emissions is positive but weak and non-linear. In line with previous studies on well-being and energy or carbon footprints, the relationship appears to saturate (i.e., need satisfaction most steeply increasing at low emission levels). The saturation point is at the emission level lower than the 2030 1.5-degree compatible target (∼300 kg CO2/year/person). A sizeable group (∼30 %) satisfies their transport needs at low emission levels (i.e., sufficiency condition). Exploratory spatial data analysis reveals that members of this group cluster in Poznan city center. All BE characteristics significantly and strongly influence the outcome variables, with central, densely populated, and walkable locations increasing the odds of having one's needs met at low emission levels. Retirees comprise about half of the sufficiency group, but there are also many workers. Specific transport needs that negatively impact the ability to meet one's needs at low emission levels, including multiple locations and doing errands on the way from or to work. The results support land use policies that reduce travel distances (i.e., densification, preventing sprawl, promoting walkable street designs) as they support low-carbon access to necessary activities for all social groups. Suburban residential locations, in turn, are associated with low need satisfaction and high emissions. The results also highlight that the ability to meet one's transport needs within the emission threshold is spatially and individually differentiated, with implications for climate policies in the mobility domain.
【摘要翻译】
这篇文章研究了日常出行温室气体（GHG）排放与交通需求自我满意度之间的关系。它还探讨了在与国际商定的2030年减排目标兼容的排放水平下，满足个人交通需求的条件，以保持全球变暖在1.5摄氏度以下。研究使用了来自波兰波兹南（一个功能性城市区域，约有80万居民）的代表性地理问卷调查，共有550名参与者回答了研究中使用的问题。通过地理空间方法计算了四个建成环境（BE）和可达性度量，并将其用作预测低/高排放水平、低/高需求满意度水平及其组合（即社会-生态象限）的预测因子，同时还考虑了社会人口特征以及与交通相关的资源、能力和责任。交通需求满意度与GHG排放之间的关系是正的，但微弱且非线性。与之前关于福祉和能源或碳足迹的研究一致，这种关系似乎饱和了（即在低排放水平下需求满意度最陡峭地增加）。饱和点在2030年1.5度兼容目标以下的排放水平（每人每年约300公斤CO2/年）。相当大的群体（约30%）在低排放水平下满足了他们的交通需求（即充足条件）。探索性空间数据分析显示，这个群体的成员在波兹南市中心聚集。所有BE特征都显著且强烈地影响结果变量，中心、人口密集和可步行的地点增加了在低排放水平下满足需求的可能性。退休人员约占充足群体的一半，但也有许多工作者。特定的交通需求，包括多个地点和在上下班途中办事，对在低排放水平下满足需求的能力产生负面影响。研究结果支持减少出行距离的土地使用政策（即密集化、防止蔓延、促进可步行街道设计），因为它们支持所有社会群体低碳访问必要的活动。反过来，郊区住宅地点与低需求满意度和高排放相关联。结果还突出表明，满足个人交通需求的能力在排放阈值内是空间和个体差异化的，这对气候政策在移动性领域有影响。
![]()
-----------关注公众号----------
