以大型语言模式建模城市概念与城市观建模:系统审查
Modeling urban perception with large language models: A systematic review
Cities (Elsevier) · Cities
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10月
Xi'an 绘图生命力:将Jacobs的标准与机器学习相结合,促进城市再生
Mapping vitality in Xi'an: Integrating Jacobs' criteria with machine learning for urban regeneration
Cities (Elsevier) · Cities
预测优化桥（POB）：代理模型辅助的随机森林—NSGA-II 节能车辆路径框架
The Prediction Optimization Bridge (POB): A Surrogate Assisted Random Forest–NSGA-II Framework for Energy Efficient Vehicle Routing
Urban Science (MDPI) · Urban Science
生成式人工智能与城市规划：系统综述及负责任城市未来的人机共创框架
Generative AI in Urban Planning: A Systematic Review and Human–AI Co-Creation Framework for Responsible Urban Futures
Journal of Planning Literature
本文依据PRISMA指南，综述2015—2025年间63篇同行评审论文及部分学术预印本，梳理六类模型、五个应用领域和五种人类角色。研究发现，现有工作侧重问题界定与约束设定，对迭代共创、以人为本的评估、治理和部署关注不足，并提出贯穿全流程、维护人类判断与制度问责的角色完整型AI城市主义。
收缩型城市的街道空间品质与居民主观情绪：基于街景图像和LLM-BERT的深度学习框架
Street spatial quality and residents' subjective emotions in a shrinking city: A deep learning framework using street view imagery and LLM-BERT
Applied Geography
中国长三角地区城市住宅建筑气候适应性改造策略：可解释机器学习与优化
Retrofit strategies for climate adaptation of urban residential buildings in the Yangtze River Delta region of China: interpretable machine learning and optimization
Building and Environment
从冷岛供给到热岛需求：基于可解释机器学习的复合降温网络与沿海城市热缓解
From cold-island supply to heat-island demand: Interpretable machine learning-informed composite cooling networks for coastal urban heat mitigation
Urban Climate
探索城市设计中可持续性和文化价值的相互作用:通过机器学习(ML)洞察模型分析当代景观
Exploring the interplay of sustainability and cultural values in urban design: Analyzing contemporary landscapes through machine learning (ML) insights modeling
Cities (Elsevier) · Cities
建立循证区划:土地利用兼容性评估的机器学习框架
Toward evidence-based zoning: A machine learning framework for land use compatibility assessment
Cities (Elsevier) · Cities
利用可解释的混合机学习框架,探讨城市内部建成环境对碳排放的非线性影响
Exploring the nonlinear impacts of the intra-urban built environment on carbon emissions using an interpretable ensemble machine learning framework
Habitat International
数字与实体融合能否有效遏制城市蔓延？来自中国的双重／去偏机器学习证据
Can digital-real integration effectively curb urban sprawl? Evidence from China using double/debiased machine learning
Land Use Policy
高密度城市灰绿基础设施形态的空间精细化调控以缓解PM2.5：可解释的MSPA—机器学习框架
Spatially explicit morphological regulation of gray-green infrastructure for PM2.5 mitigation in high-density cities: An interpretable MSPA-machine learning framework
Building and Environment
注意利益错位：利用大语言模型绘制西方主要英语地区城市电动出行利益相关方的利益分歧
Mind the mismatch: mapping stakeholder-interest divergence in urban e-mobility across major western anglophone arenas using large language models
Transportation Research Part A: Policy and Practice · Transportation Research Part A Policy and Practice
利用可解释的机器学习和空间热点分析进行城市道路事故严重性预测:厄瓜多尔洛哈的证据
Urban Road Crash Severity Prediction Using Explainable Machine Learning and Spatial Hotspot Analysis: Evidence from Loja, Ecuador
Urban Science (MDPI) · Urban Science
2014-2025年哈萨克斯坦区域创新差异:官方小组的投入-产出失调,2014-2025年
Regional Innovation Disparities in Kazakhstan: Input–Output Misalignment in an Official Panel, 2014–2025
Urban Science (MDPI) · Urban Science
为城市出行目的调整大型语言模式的推断:一个了解域域的文字表述和微调框架
Adapting large language models for urban trip purpose inference: A domain-informed textual representation and fine-tuning framework
Cities (Elsevier) · Cities
空间机器学习方法：分析与糖尿病诊断相关的急诊就诊人口层面因素
A Spatial Machine Learning Approach for Analyzing Population-Level Factors Associated with Emergency Department Visits with Diabetes Diagnoses
Journal of Urban Health
研究利用空间机器学习和统计方法，分析马里兰州邮政编码制表区中与糖尿病相关急诊就诊有关的人口层面因素，并按种族和居住隔离程度分层。结果显示，住房空置、交通繁忙、绿地及休闲活动和吸烟等健康行为与各群体的就诊相关；相关因素因种族和居住隔离模式而异，交通繁忙尤其与黑人患者较高的就诊几率相关。
将问责制作为基础设施：人工智能赋能规划权力的设计理论
Accountability as Infrastructure: A Design Theory of AI-Enabled Planning Authority
Journal of the American Planning Association
本文提出并诊断性应用一套设计理论，旨在确保人工智能支持的规划权力在部署后仍可接受公众审查、质疑和撤回。研究整合六种问责工具，并将框架用于佛罗里达州盖恩斯维尔的微出行项目，识别出系统用途未经授权扩张、监督弱化和分配绩效持续不佳三类风险。作者建议按风险分级设置审查、公开信息、复核门槛及定期续审要求，并通过采购合同保障审计与终止权。
连接LiDAR与NAIP：可扩展的深度学习框架，用于全州城市树冠制图
Bridging LiDAR and NAIP: A scalable deep learning framework for statewide urban tree canopy mapping
Urban Forestry & Urban Greening · Urban forestry & urban greening
城市居民是否受困于高温？基于出行的热隔离分析
Are urban residents trapped by high temperatures? A travel-based heat segregation analysis
Transportation Research Part D: Transport and Environment · Transportation Research Part D Transport and Environment
研究提出基于出行的热隔离指数，并将其应用于中国深圳的无桩共享单车出行数据和昼夜地表温度数据。空间分析与可解释机器学习显示，热隔离普遍存在，高温与高隔离集聚区主要位于外围城区。出行多样性、流量变化和OD出行空间范围扩大通常与较低热隔离相关，研究据此提出有针对性且适应时段变化的热缓解策略。