基于多步机器学习数据融合方法的复杂城市区域街区尺度气温估算
Neighbourhood-scale estimation of air temperature in complex urban areas using a multistep machine learning-based data fusion approach
Urban Climate
城市人工智能与基础模型
所属领域：城市数据科学与方法.
近12个月每月收录量
2026年6月
从在线评论揭示多感官景观体验：基于大语言模型的方法及其对以人为本土地利用政策的启示
Unfolding the multisensory landscape experiences from online reviews: A large language model based approach with implications for human-centric land use policy
Land Use Policy
基于机器学习的城郊地下水水质综合预测：希腊阿提卡地区案例
Integrated Machine Learning Based Groundwater Quality Prediction in a Peri-Urban Area: The Case of Attica Region, Greece
Urban Science (MDPI) · Urban Science
研究利用希腊阿提卡河流域80个监测站的958条观测记录，结合MICE-PMM缺失值插补与TabNet、SVM和GBM模型预测地下水水质指数。MICE-PMM与TabNet组合表现最佳，R²和NSE均为0.91；特征分析显示硝酸盐是水质指数变化的主要驱动因素。
家庭能源管理系统的优化技术：综合综述、批判性分析与未来方向
Optimization Techniques for Home Energy Management Systems: A Comprehensive Review, Critical Analysis, and Future Directions
Urban Science (MDPI) · Urban Science
本文综述并批判性分析家庭能源管理系统中的优化技术，涵盖数学方法、元启发式算法、人工智能方法和规则策略，并比较其可扩展性、计算复杂度、不确定性处理及实时适用性。文章指出，多目标优化、不确定性与电动汽车整合及现实应用仍有不足，并提出混合优化和物联网智能能源管理等研究方向。
无家可归与隐私：城市人工智能和智能技术带来的挑战
Homelessness and privacy: challenges from AI and smart technologies in the city
Urban Geography
文章借助海伦·尼森鲍姆的“情境完整性”隐私理论，探讨人工智能和智能技术在公共与集体空间、个人技术使用及救助空间三种情境中对无家可归者隐私的影响。研究指出，这些技术改变了既有信息共享规范，使信息尤其是私密信息更易流转，并改变解释与决策过程。由此既可能带来惩罚风险上升、个人能动性下降等危险，也可能增强保护与能动性，凸显进一步研究相关伦理问题及提升无家可归者能动性的必要。
重新构想雨水花园：城市雨水滞蓄与入渗的计算方法
Rain garden reimagined: A computational approach to urban water retention and infiltration
Building and Environment
研究在波兰弗罗茨瓦夫开展田间试验，利用机器学习预测地面雨水花园在不同降雨和环境条件下能否滞蓄径流。结果显示，滞蓄与降雨总量、强度和持续时间密切相关；人工神经网络和逻辑回归准确率最高，均为99.0%。
居住在城市中心区会增加私人汽车使用吗？一种应对居住地自我选择偏差的双重机器学习方法
Does residing in central urban areas increase private vehicle use? A double machine learning method to address residential self-selection bias
Journal of Transport Geography
优化城市树木结构风险评估：融合专家知识与多源数据的可解释机器学习框架
Optimizing urban tree structural risk assessment: An explainable machine learning framework integrating expert knowledge and multi-source data
Urban Forestry & Urban Greening · Urban forestry & urban greening
面向城市决策支持的可解释人工智能房地产预测：机器学习框架
Explainable AI for Urban Real-Estate Prediction: A Machine-Learning Framework for Urban Decision Support
Urban Science (MDPI) · Urban Science
本文提出RE-VAL（房地产估值）可解释分析框架，整合可复现的数据获取、地理信息特征处理、预测基准比较和可解释输出。对意大利卡利亚里1153条住宅挂牌信息的比较显示，MLP预测表现最佳，随机森林则兼具较强预测能力与可解释性。框架利用SHAP分解生成透明的货币化“加分/减分”调整表，并揭示潜在的非线性交互关系。
以城市形态表征住房与基础设施不平等：基于开放建筑轮廓数据的机器学习方法
Urban morphology as a proxy for housing and infrastructure inequality: A machine learning approach using open building footprint data
Computers, Environment and Urban Systems
气候韧性政策对城市碳强度的影响：计量经济学与机器学习的证据
Impact of climate resilience policy on urban carbon intensity: Evidence from econometrics and machine learning
Cities (Elsevier) · Cities
产业迁移对城市污染防治的影响：基于机器学习方法的政策异质性效应分析
The impact of industrial relocation on urban pollution prevention and control: Insights from heterogeneous policy effects based on machine learning methods
Cities (Elsevier) · Cities
东京大都市区城市收缩的环境驱动因素：非线性与空间异质性的机器学习分析
Environmental drivers of urban shrinkage in the Tokyo metropolitan area: A machine learning analysis of nonlinearity and spatial heterogeneity
Habitat International
城市收缩，健康不退：基于深度学习方法研究收缩城市街道空间健康绩效的演变
Shrinking cities, unshrinkable health: A study on the evolution of street spatial health performance in shrinking cities based on deep learning methods
Habitat International
生成式人工智能用于自动化城市生态评估，仍需大量人工监督
Generative artificial intelligence use in automated urban ecological assessments requires substantial human oversight
Landscape and Urban Planning
协同优化城市街区内多尺度空间形态以提升低碳绩效：机器学习驱动的设计支持框架
Collaboratively optimize of multi-scale spatial form within urban blocks for low-carbon performance: A machine learning-driven design support framework
Sustainable Cities and Society
灰绿空间格局对扩张型与收缩型城市碳排放和碳汇的影响：一种可解释机器学习方法
Impacts of grey-green spatial patterns on carbon emissions and sequestration in expanding and shrinking cities: An explainable machine learning approach
Sustainable Cities and Society
基于街道尺度形态与功能特征的城市噪声水平可解释机器学习研究
Interpretable machine learning of urban noise levels from street-scale morphology and functionality
Sustainable Cities and Society
运用可解释机器学习与政策模拟促进城市公园出行绿色化
Promoting green mobility for urban park visits through explainable machine learning and policy simulation
Sustainable Cities and Society
自然—建成环境如何塑造城市热岛的时空格局：整合水体梯度分层与机器学习
How natural–built environments shape spatiotemporal patterns of urban heat islands: Integrating water-gradient stratification and machine learning
Sustainable Cities and Society