基于GAN的北京传统住宅小区室外热舒适度建模

本文研究了在全球气候变暖背景下，城市热浪事件对居民健康和生活质量的影响。研究目的在于解决传统数值模拟方法在计算户外热舒适度（UTCI）时的高成本和低效率问题。通过提出基于生成对抗网络（GAN）的UTCI预测方法，实现了快速、准确的户外热舒适度评估。研究方法包括借助Rhino/Grasshopper平台构建城市模型、使用Ladybug和Eddy3D插件进行气候模拟、基于TensorFlow框架训练pix2pix对抗网络模型，并通过实验验证了模型的预测性能。研究结果表明，pix2pix模型在预测城市环境舒适度方面表现出色，显著提高了预测速度并降低了数据收集成本，为城市设计和可持续建设提供了科学依据。
This article studies the impact of urban heat wave events on residents' health and quality of life in the context of global climate warming. The purpose of the research is to solve the high cost and low efficiency problems of traditional numerical simulation methods in calculating outdoor thermal comfort (UTCI). By proposing a UTCI prediction method based on a generative adversarial network (GAN), a fast and accurate outdoor thermal comfort assessment is achieved. Research methods include using the Rhino/Grasshopper platform to build city models, using Ladybug and Eddy3D plug-ins for climate simulation, training the pix2pix adversarial network model based on the TensorFlow framework, and verifying the prediction performance of the model through experiments. Research results show that the pix2pix model performs well in predicting urban environmental comfort, significantly improves prediction speed and reduces data collection costs, providing a scientific basis for urban design and sustainable construction.

街道建筑环境对 SARS-CoV-2 传播的影响：以香港为例

本研究探讨了街道级建成环境（SLBE）对SARS-CoV-2传播风险（SSTR）的影响，重点关注香港疫情的前五波。研究发现，在高风险区域，街道人行道、卫生设施和人工结构是主要风险因素；在低风险区域，交通控制设施与SSTR正相关。不同疫情波次中，SLBE特征的影响有所不同，随机森林模型在解释SSTR与SLBE的非线性关系上表现最佳。研究提出了优化SLBE以降低传播风险的政策建议，为城市规划和政策制定提供参考。
This study explores the impact of street-level built environment (SLBE) on SARS-CoV-2 transmission risk (SSTR), focusing on the first five waves of the epidemic in Hong Kong. The study found that in high-risk areas, street sidewalks, sanitation facilities and artificial structures are the main risk factors; in low-risk areas, traffic control facilities are positively related to SSTR. In different epidemic waves, the impact of SLBE characteristics is different, and the random forest model performs best in explaining the nonlinear relationship between SSTR and SLBE. The study puts forward policy recommendations for optimizing SLBE to reduce transmission risks, providing a reference for urban planning and policy formulation.

上海市养老助餐空间可达性及其影响因素研究

本文拟解决的科学问题在于：基于生活圈尺度视角，如何评价上海市助餐设施与老年人口的匹配情况，如何划定分割标准进行助餐可达性水平评价，如何计算各小区目前的助餐设施缺失数量，如何评价上海市助餐空间布局的均衡性，以及在此基础上如何识别助餐可达性分布的影响因素。
The scientific problems that this paper aims to solve are: Based on the perspective of life-circle scale, this paper discusses how to evaluate the match between the assisted meal facilities and the elderly population in Shanghai, how to delimit the segmentation criteria to evaluate the level of assisted meal accessibility, how to calculate the number of missing assisted meal facilities in each community, how to evaluate the balance of the spatial layout of assisted meal in Shanghai, and how to identify the influencing factors of the distribution of assisted meal accessibility on this basis.

基于大数据的老年人服务空间分布失衡量化研究

本文基于北京石景山区218个小区，通过空间分析和机器学习的方法。探讨老年人服务设施分布和老年人死亡率代表的老年人生活质量之间的影响因子。结论显示交通设施的密度、医疗设施、生活服务设施、老年保健设施的可访问性关系最大，这为未来的城市规划和老龄化社会建设提供了建设。
This paper is based on 218 residential areas in Shijingshan District of Beijing, through spatial analysis and machine learning methods. To explore the influencing factors between the distribution of service facilities for the elderly and the quality of life represented by the mortality rate of the elderly. The conclusion shows that the density of transportation facilities, medical facilities, living service facilities and elderly health care facilities have the largest accessibility relationship, which provides construction for future urban planning and the construction of an aging society.

机器学习在历史保护街区活力分析上的应用

本文基于北京市有的八个历史街区，运用机器学习的方法对分为23个因子（形态、功能、视觉和交通四个方面）的活力特征进行分析建模，以便更好地管理历史保护街区。
Based on eight historic blocks in Beijing, this paper uses machine learning to analyze and model the dynamic characteristics divided into 23 factors (form, function, vision and traffic), so as to better manage historic protected blocks.