城市研究SCI杂志论文概览_第一期

城市数据研习社

已于 2024-07-27 15:50:46 修改

阅读量164

点赞数 1

分类专栏：学术研究论文概览文章标签：学习科技

于 2024-07-08 14:44:45 首次发布

本文链接：https://blog.csdn.net/lfsjxs/article/details/140268524

版权

学术研究同时被 2 个专栏收录

2 篇文章 0 订阅

订阅专栏

论文概览

2 篇文章 0 订阅

订阅专栏

本次给大家整理的是《Computers, Environment and Urban Systems》杂志2024年7月第111期的论文的题目和摘要，一共包括6篇SCI论文！

【论文1】

Machine learning to model gentrification: A synthesis of emerging forms

用机器学习模拟老城区翻新：各类新兴形式的综合分析

【摘要】

Gentrification is a complex and context-specific process that involves changes in the built environment and social fabric of neighborhoods, often resulting in the displacement of vulnerable communities. Machine Learning (ML) has emerged as a powerful predictive tool that is capable of circumventing the methodological challenges that historically held back researchers from producing reliable forecasts of gentrification. Additionally, computer vision ML algorithms for landscape character assessment, or deep mapping, can now capture a wider range of built metrics related to gentrification-induced redevelopment. These novel ML applications promise to rapidly progress our understandings of gentrification and our capacity to translate academic findings into more productive direction for communities and stakeholders, but with this sudden development comes a steep learning curve. The current paper aims to bridge this divide by providing an overview of recent progress and an actionable template of use that is accessible for researchers across a wide array of academic fields. As a secondary point of emphasis, the review goes over Explainable Artificial Intelligence (XAI) tools for gentrification models and opens up discussion on the nuanced challenges that arise when applying black-box models to human systems.

【摘要翻译】

老城区翻新是一个复杂且具体情境依赖的过程，涉及到社区建筑环境和社会结构的变化，往往导致弱势群体的流离失所。机器学习（ML）已经成为一种强大的预测工具，能够克服历史上阻碍研究人员产生可靠翻新预测的方法学挑战。此外，用于景观特征评估或深度映射的计算机视觉ML算法现在能够捕捉到更广泛的与翻新驱动的再开发相关的建筑指标。这些新颖的ML应用承诺能迅速推进我们对老城区翻新的理解以及我们将学术发现转化为对社区和利益相关者更有成效方向的能力，但这种突然的发展也带来了陡峭的学习曲线。当前论文旨在通过提供最近进展的概述和一个可供广泛学术领域的研究人员使用的行动模板来弥合这一差距。作为次要重点，本综述还讨论了用于构建老城区翻新模型的可解释人工智能（XAI）工具，并开启了关于在将黑箱模型应用到人类系统时所出现的微妙挑战的讨论。

【作者信息】

Mueller Maya，美国德雷塞尔大学土木、建筑和环境工程系

Hoque Simi，美国德雷塞尔大学土木、建筑和环境工程系， sth55@drexel.edu 

Hamil Pearsall，美国天普大学地理与城市研究系

【论文2】

Predicting building characteristics at urban scale using graph neural networks and street-level context

使用图神经网络和街道级场景预测城市量级的建筑物特征

【摘要】

Building characteristics, such as number of storeys and type, play a key role across many domains: interpreting urban form, simulating urban microclimate or modelling building energy. However, geospatial data on the building stock is often fragmented and incomplete. Here, we propose a novel and easily adaptable method to predict building characteristics in diverse cities, which attempts to mitigate such data gaps. Our method exploits the geospatial connectivity between street-level urban objects and building characteristics by employing graph neural networks, as they can model spatial relationships and leverage them for predictions. We apply this approach in three representative cities (Boston, Melbourne, and Helsinki) that offer a variety of building features as prediction targets (storeys, types, construction period and materials) and diverse urban environments as predictors. Overall, the magnitude of errors is acceptable for a series of use cases. In the prediction of building storeys, an average of 81.83% buildings in three cities have less than one-storey prediction error. We also find that the prediction of building type achieves an average of 88.33% accuracy across three cities. Meanwhile, an average of 70.5% of buildings are correctly classified by construction period in Melbourne and Helsinki, and the building material prediction accuracy is 68% in Helsinki. The results confirm that our approach is adaptable across different urban environments because comparable performance is achieved in the other two cities. Further, we assess the impact of varying local data availability on model performance. Our findings underscore the feasibility of the method in scenarios with sparse building data (10%, 30% and 50% availability). Our graph-based approach advances research on filling in incomplete building semantics from existing datasets, and showcases the potential to enable 3D city modelling. Given the broad applicability of the approach to predicting many building characteristics, diverse downstream applications exist, such as enhancing contemporary urban studies (e.g. exploring streetscapes) and facilitating the development of 3D GIS (e.g. maintaining and updating 3D building settings).

【摘要翻译】

建筑特征（例如楼层数和类型）在许多领域都发挥着关键作用：解释城市形态、模拟城市微气候或建模建筑能量。然而，建筑物存量的地理空间数据往往是零散和不完整的。在这里，我们提出了一种新颖且易于适应的方法来预测不同城市的建筑特征，试图弥补这种数据差距。我们的方法利用图神经网络来利用街道级城市物体和建筑特征之间的地理空间连通性，因为它们可以对空间关系进行建模并利用它们进行预测。我们在三个代表性城市（波士顿、墨尔本和赫尔辛基）应用了这种方法，这些城市提供各种建筑特征作为预测目标（楼层、类型、施工时间和材料）和各种城市环境作为预测因子。总体而言，对于一系列用例来说，误差幅度是可以接受的。在建筑楼层的预测中，三个城市中平均有 81.83% 的建筑的预测误差小于一层。我们还发现，在三个城市中，建筑类型的预测平均准确率为 88.33%。同时，墨尔本和赫尔辛基的建筑物按施工期分类的平均准确率为 70.5%，赫尔辛基的建筑材料预测准确率为 68%。结果证实，我们的方法适用于不同的城市环境，因为在其他两个城市中也实现了类似的性能。此外，我们评估了不同本地数据可用性对模型性能的影响。我们的研究结果强调了该方法在建筑数据稀疏（10%、30% 和 50% 可用性）场景中的可行性。我们基于图的方法推动了从现有数据集中填充不完整建筑语义的研究，并展示了实现 3D 城市建模的潜力。鉴于该方法在预测许多建筑特征方面的广泛适用性，存在各种下游应用，例如增强当代城市研究（例如探索街景）和促进 3D GIS 的发展（例如维护和更新 3D 建筑设置）。

【作者信息】

Binyu Lei，新加坡国立大学建筑系

Pengyuan Liu，未来城市实验室全球，新加坡ETH中心，新加坡

Nikola Milojevic-Dupont，德国墨卡托全球公共和气候变化研究所

Filip Biljecki，新加坡国立大学建筑系，filip@nus.edu.sg

【论文3】

From cell tower location to user location: Understanding the spatial uncertainty of mobile phone network data in human mobility research

手机信号塔定位到用户定位：了解人类出行研究中移动电话网络数据的空间不确定性

【摘要】

Mobile phone network data is a vital source for unveiling human mobility characteristics in accordance with its large-scale spatiotemporal trajectory information. However, mobile phone network data usually records location at the level of cell towers, lacking accurate individual locations. Therefore, the authenticity and credibility of the conclusions drawn from such data are often questioned due to the spatial uncertainty. In this paper, we evaluate the location differences between users and the cell towers during connection establishment. Furthermore, we delve into the representation and contributing factors of spatial uncertainty, including cell tower density, antenna status, and user mobility. Our analysis is based on one-month mobile signaling data and taxi GPS data collected in Foshan (a prefecture-level city in China), which represent two forms of data on the mobility of the same individual. We conclude that to estimate user positions, areas significantly larger than the nearest cell tower are necessary. The influence of tower density and antenna load on connection accuracy does not exhibit a straightforward linear dependency; instead, it fluctuates once a threshold is reached. Connection accuracy is typically higher when users are stationary than when they are in motion. Our findings together indicate that it should carefully assess the accuracy of position estimation when mapping from cell tower location to user location.

【摘要翻译】

手机网络数据是揭示人类移动特征的重要来源，因为它具有大规模的时空轨迹信息。然而，手机网络数据通常记录的是基站级别的位置，缺乏准确的个人位置。因此，由于空间不确定性，从这些数据中得出的结论的真实性和可信度常常受到质疑。在本文中，我们评估了连接建立过程中用户和基站之间的位置差异。此外，我们深入研究了空间不确定性的表现形式和影响因素，包括基站密度、天线状态和用户移动性。我们的分析基于佛山（中国地级市）收集的一个月的移动信令数据和出租车 GPS 数据，它们代表了同一个人的两种移动数据形式。我们得出结论，要估计用户位置，需要比最近的基站大得多的区域。塔密度和天线负载对连接精度的影响并不表现出直接的线性依赖性；相反，一旦达到阈值，它就会波动。用户静止时的连接精度通常高于运动时。我们的研究结果表明，在从手机信号塔位置映射到用户位置时，应该仔细评估位置估计的准确性。

【作者信息】

Xiangkai Zhou, 中山大学智能系统工程学院, 中国.

Linlin You, 中山大学智能系统工程学院, 中国.

Shuqi Zhong, 中山大学智能系统工程学院, 中国.

Ming Cai, 中山大学智能系统工程学院, 中国, caiming@mail.sysu.edu.cn

【论文4】

How can SHAP (SHapley Additive exPlanations) interpretations improve deep learning based urban cellular automata model?

SHAP（SHapley Additive exPlanations）解释如何改进基于深度学习的城市元胞自动机模型？

【摘要】

Interpretations of the urban cellular automata (CA) model aim to ensure that its predictive behaviors are consistent with real-world processes. Current urban CA interpretations have revealed the impacts of driving factors on land development suitability, or neighborhood effects and random perturbation on simulation results. However, three limitations remain unresolved: (1) the interpretations of deep learning (DL)-based urban CA are seldom integrated with the prerequired feature selection, (2) the input features from different urban CA modules are still explained by separate approaches, and (3) the interpretation results are rarely derived at the cell level to uncover spatially varying urban land development patterns. This study proposes a SHapley Additive exPlanations (SHAP)-based urban CA interpretation framework to address these challenges and improve urban CA. This framework uses model-level SHAP importance to identify dominant features from different modules for constructing the final simulation model. Then, cell-level SHAP importance is used to uncover spatially varying driving forces of urban expansion. The framework's effectiveness is rigorously tested and confirmed using a convolution neural network CA (CNN-CA) model for Dongguan City. The experimental results demonstrate that (1) SHAP-based model interpretation improves feature selection for DL-based urban CA. The figure of merit for CNN-CA calibrated using SHAP-based important features improves by 3%, outperforming the tested baseline methods. (2) SHAP measures the impacts of each feature from different CA modules in a whole. In this case, physical factors are much more important at the model level than proximity and accessibility factors, while neighborhood effect is the second most crucial factor. (3) Cell-level SHAP interpretations uncover spatially different urban land development patterns. For example, due to the extensive industrial land development in the northern Songshan Lake Zone, in the CNN-CA model, proximity to major roads within this region is associated with positive SHAP-based contribution share on cell-level urban expansion.

【摘要翻译】

对城市元胞自动机 (CA) 模型的解释旨在确保其预测行为与现实世界的过程一致。当前的城市 CA 解释揭示了驱动因素对土地开发适宜性的影响，或邻里效应和随机扰动对模拟结果的影响。然而，仍存在三个限制：(1) 基于深度学习 (DL) 的城市 CA 的解释很少与预先要求的特征选择相结合，(2) 来自不同城市 CA 模块的输入特征仍然由单独的方法解释，(3) 解释结果很少在单元级别得出，以揭示空间变化的城市土地开发模式。本研究提出了一种基于 SHapley Additive exPlanations (SHAP) 的城市 CA 解释框架来应对这些挑战并改进城市 CA。该框架使用模型级 SHAP 重要性来识别来自不同模块的主导特征，以构建最终的模拟模型。然后，使用单元级 SHAP 重要性来揭示城市扩张的空间变化驱动力。使用东莞市的卷积神经网络CA（CNN-CA）模型严格测试并确认了该框架的有效性。实验结果表明：（1）基于SHAP的模型解释改进了基于DL的城市CA的特征选择。使用基于SHAP的重要特征校准的CNN-CA的品质因数提高了3％，优于测试过的基线方法。（2）SHAP整体上衡量来自不同CA模块的每个特征的影响。在这种情况下，物理因素在模型层面比接近度和可达性因素重要得多，而邻里效应是第二重要的因素。（3）单元级SHAP解释揭示了空间上不同的城市土地发展模式。例如，由于北部松山湖区大规模的工业用地开发，在CNN-CA模型中，该地区与主要道路的接近度与基于SHAP的单元级城市扩张的正贡献份额相关。

【作者信息】

Changlan Yang, 武汉大学资源与环境科学学院, 中国。

Xuefeng Guan, 武汉大学测绘与遥感信息工程国家重点实验室,  guanxuefeng@whu.edu.cn

Qingyang Xu, 武汉大学测绘与遥感信息工程国家重点实验室。

Weiran Xing, 武汉大学测绘与遥感信息工程国家重点实验室。

Xiaoyu Chen, 武汉大学测绘与遥感信息工程国家重点实验室。

Jinguo Chen, 湖北省地质局三队。

Peng Jia, 武汉大学资源与环境科学学院。

【论文5】

UrbanClassifier: A deep learning-based model for automated typology and temporal analysis of urban fabric across multiple spatial scales and viewpoints

UrbanClassifier：一种基于深度学习用于跨多个空间尺度和视角对城市结构进行自动类型学和时间分析的模型

【摘要】

The field of urban morphology, crucial for understanding the evolutionary trajectories of cityscapes, has traditionally depended on manual classification methods. The surge in deep learning and computer vision technologies presents an opportunity to automate and enhance urban typo-morphology studies. This research addresses three critical shortcomings in the current body of work: the neglect of urban fabric's three-dimensional qualities, the homogeneity of spatial scales in dataset creation and the dependence on a single-perspective for urban fabric classification. A novel deep learning-based model, UrbanClassifier, is introduced, trained on a substantial dataset that encapsulates the three-dimensionality of urban fabric along with morphological types and development periods. Extensive experimentation across four European cities highlights the model's ability to incorporate diverse spatial scales and viewpoints in urban fabric analysis. The UrbanClassifier exemplifies a method integrating features from various scales and perspectives, thus laying the groundwork for scalable and accessible urban typo-morphology studies, aiding practitioners in discerning the spatio-temporal evolution of urban fabric.

【摘要翻译】

城市形态学领域对于理解城市景观的演变轨迹至关重要，传统上依赖于手动分类方法。深度学习和计算机视觉技术的激增为自动化和增强城市类型形态学研究提供了机会。这项研究解决了当前工作中的三个关键缺陷：忽视城市结构的三维特性、数据集创建中的空间尺度同质性以及对城市结构分类的单一视角的依赖。引入了一种基于深度学习的新型模型 UrbanClassifier，该模型在一个包含城市结构的三维性以及形态类型和发展时期的大量数据集上进行训练。在四个欧洲城市进行的广泛实验凸显了该模型在城市结构分析中融入不同空间尺度和观点的能力。UrbanClassifier 是一种整合不同尺度和视角特征的方法，从而为可扩展和可访问的城市类型形态学研究奠定了基础，帮助从业者辨别城市结构的时空演变。

【作者信息】

Zhou Fang, 清华大学建筑学院, 中国.

Ying Jin, Martin Centre for Architectural and Urban Studies, University of Cambridge, UK.

Shuwen Zheng, 清华大学建筑学院, 中国.

Liang Zhao, 清华大学建筑学院, 中国,  zhaoliang@tsinghua.edu.cn

Tianren Yang, 香港大学城市规划与设计学系，中国香港,  tianren@hku.hk

【论文6】

A hybrid deep learning method for identifying topics in large-scale urban text data: Benefits and trade-offs

一种用于识别大规模城市文本数据中主题的混合深度学习方法：优点与权衡

【摘要】

Large-scale text data from public sources, including social media or online platforms, can expand urban planners' ability to monitor and analyze urban conditions in near real-time. To overcome scalability challenges of manual techniques for qualitative data analysis, researchers and practitioners have turned to computer-automated methods, such as natural language processing (NLP) and deep learning. However, the benefits, challenges, and trade-offs of these methods remain poorly understood. How much meaning can different NLP techniques capture and how do their results compare to traditional manual techniques? Drawing on 90,000 online rental listings in Los Angeles County, this study proposes and compares manual, semi-automated, and fully automated methods for identifying context-informed topics in unstructured, user-generated text data. We find that fully automated methods perform best with more-structured text, but struggle to separate topics in free-flow text and when handling nuanced language. Introducing a manual technique first on a small data set to train a semi-automated method, however, improves accuracy even as the structure of the text degrades. We argue that while fully automated NLP methods are attractive replacements for scaling manual techniques, leveraging the contextual understanding of human expertise alongside efficient computer-based methods like BERT models generates better accuracy without sacrificing scalability.

【摘要翻译】

来自公共来源（包括社交媒体或在线平台）的大规模文本数据可以扩展城市规划人员近乎实时地监测和分析城市状况的能力。为了克服定性数据分析中手动技术的可扩展性挑战，研究人员和从业者已转向计算机自动化方法，例如自然语言处理 (NLP) 和深度学习。然而，这些方法的优势、挑战和权衡仍然不太清楚。不同的 NLP 技术可以捕捉多少含义，它们的结果与传统的手动技术相比如何？本研究利用洛杉矶县的 90,000 个在线租赁清单，提出并比较了手动、半自动和全自动方法，用于在非结构化、用户生成的文本数据中识别上下文信息主题。我们发现全自动方法在更结构化的文本中表现最佳，但在自由流文本和处理细微差别的语言时难以区分主题。然而，首先在小数据集上引入手动技术来训练半自动化方法，即使文本结构退化，也能提高准确性。我们认为，虽然全自动 NLP 方法是扩展手动技术的有吸引力的替代品，但利用对人类专业知识的上下文理解以及 BERT 模型等高效的基于计算机的方法可以在不牺牲可扩展性的情况下产生更好的准确性。