Smart Cities, Digital Twins and Large Language Models

Generative artificial intelligence (GenAI) models are increasingly used for scientific data generation, yet their alignment with em- pirical knowledge in urban science remains unclear. We therefore ask whether generated urban data reproduce empirical regularities and support repeatable experiments. We in- troduce AI4US, a framework for evaluating data synthesis and conditional intervention across text and image modalities. Four cases spanning urban systems, within-city struc- ture, neighbourhood vitality and streetscape perception are evaluated against published parameters, observed urban data and human judgements. Generated outputs recovered recognizable scaling and distance-decay pat- terns and yielded measurable associations be- tween neighbourhood morphology indicators and pedestrian activity, while model judge- ments showed positive agreement with sam- pled human choices. Controlled changes to urban conditions produced repeatable out- put responses across all four cases. How- ever, generated data often compressed empir- ical numerical coverage, local variation and visual diversity. In an inspectable GenAI model, intermediate activations linearly dis- tinguished some urban relationships, while activation edits changed only selected out- put scores. AI4US provides an empirically grounded approach for assessing GenAI as the virtual urban laboratory in urban data synthesis and controlled model experiments, while revealing its tendency to simplify em- pirical complexity.

人工智能技术正以前所未有的速度重塑各行各业发展格局 ， 大模型作为新一轮科技革命的核心驱动力 ， 已成为推动新质生产力发展和社会治理现代化的重要引擎 。 为系统探索自然资源行业大模型发展的理论认知 、 技术路径 、 应用模式和治理机制 ， 特邀来自高等院校 、 科研院所 、 研发机构和管理部门的多位专家 ， 围绕技术创新与行业需求深度融合展开深入访谈 。 结合各位专家主要观点 ， 新时期自然资源行业大模型发展需重点关注 ：（ 1 ） 面向行业特色的专业智能体系构建与技术突破 。 针对自然资源行业时空数据复杂 、 专业知识密集 、 业务逻辑严谨等特点 ， 需要突破通用大模型在地理空间认知 、 专业知识推理 、 多尺度建模等方面的技术局限 ， 构建融合空间拓扑关系 、 时序演化规律 、 多模态数据理解的时空大模型架构 ， 实现从文本语义理解向地理智能体的跃升 ， 推动调查监测 、 空间规划 、 资源配置 、 生态保护等核心业务向物理世界大模型演进 ， 形成颠覆性的智能化范式转变 。（ 2 ） 面向业务需求的应用场景创新与价值实现路径探索 。 聚焦自然资源 “ 两统一 ” 职责履行的核心需求 ， 坚持 “ 人机协同 ” 而非 “ 机器替代 ” 的基本定位 ， 强化大模型在信息感知 、 分析认知 、 判断决策等环节的深度应用 ， 通过短期基于开源模型的分层生态快速适配与长期独立技术底座的自主可控相结合的分阶段策略 ， 重点围绕 “ 数据 —知识—模型—场景 ” 四要素协同演进机制 ， 构建覆盖宏观战略决策 、 中观业务管理 、 微观技术操作的多层次应用体系 ， 实现技术能力与业务需求的精准匹配和规模化应用转化 。（ 3 ） 面向多主体协同的治理体系构建与制度创新 。 重视自然资源数据的国家安全属性和大模型技术的 “ 双刃剑 ” 特征 ， 统筹发挥高校科研机构的策源地作用 、 自然资源主管部门的行业指导作用 、 信息技术企业的创新主体作用 ， 构建 “ 政产学研用 ” 协同创新生态体系 ， 通过建立涵盖技术层面的数据治理 、 算法审核 、 幻觉防控和制度层面的标准规范 、 法律保障 、 风险评估的全链条安全治理体系 ， 统筹处理技术创新与安全保障 、 开放共享与风险防控 、 效率提升与责任追溯的关系 ， 确保收稿日期 ： 2026 - 03 - 16 ； 修订日期 ： 2026 - 08 - 14 基金项目 ： 国家自然科学基金项目 （ 42471513 ） 作者简介 ： 张鸿辉 （ 1980 - ） ， 男 ， 湖南长沙人 ， 博士 ， 正高级工程师 ， 研究方向为地理空间智能 、 智慧国土空间规划 、 时空大数据分析 。 E-mail : 249536073 @qq . com 通讯作者 ： 钟镇涛 （ 1993 - ） ， 男 ， 新疆库尔勒人 ， 硕士 ， 测绘工程师 ， 研究方向为地理空间智能与智慧国土空间规划 。 E-mail : zztoozzt@qq . com 。 其他作者为共同第二作者 。 41 卷自然资源学报自然资源行业大模型在合理 、 合规 、 合法边界内健康有序发展 。

The rapid development of artificial intelligence (AI) is driving a profound transformation in higher education, shifting conventional teaching models toward intelligent instructional paradigms. This study explores the development of AI teaching assistant systems, their application in educational practice, and the construction of a discipline-based knowledge engine. The results demonstrate that, through the integration of domain knowledge injection, retrieval-augmented generation mechanisms, and optimized text- to-image generation capabilities, AI teaching assistants not only significantly improve the accuracy of professional knowledge question answering, but also exhibit high expressive precision and strong adaptability to Chinese local urban contexts in urban spatial scene image generation tasks. Building upon these findings, this study further proposes a pathway for constructing discipline- based knowledge engines grounded in large language models and deeply customized for disciplinary knowledge systems. A system architecture integrating text generation, knowledge graphs, and collaborative text-to-image generation is developed to facilitate the evolution from general-purpose language models to discipline- oriented intelligent engines. This research provides a replicable and transferable theoretical framework and technical pathway for the digital transformation of higher education, while also expanding the application scenarios and future directions of interdisciplinary research at the intersection of AI and education.

Shrinking cities, defined by sustained population loss and declining population density, have be- come a central concern in global urban studies and planning practice. In China, driven by industrial restruc - turing and uneven regional development, many cities are faced with multiple structural challenges, including demographic outflow, economic stagnation, and underutilized spatial resources. Against this backdrop, tradi- tional growth-oriented development models based on spatial expansion have become increasingly ineffective. Consequently, urban development paradigms are shifting from "growth-oriented" strategies toward "smart shrinkage", which emphasizes efficiency, adaptability, and resource optimization. Against this context, platform urbanism has emerged as a novel urban development model centered on digital technologies. By leveraging data and algorithmic governance, it reshapes urban operations and offers new pathways and governance tools to addressing the challenges faced by shrinking cities. Existing studies generally conceptualize platform urbanism as the deep integration of digital platforms into urban systems. Building on the data-driven logic of smart cities while incorporating the resource allocation mechanisms of platform capitalism, this approach focuses on the restructuring of urban spatial configurations, labor relations, and everyday life. However, current academic discussions predominantly focus on growing or innovative cities, highlighting the role of platforms in fostering economic growth, technological innovation, and urban competitiveness. In contrast, research on shrinking cities remains relatively limited, particularly regarding systematic examinations of the mechanisms through which platforms intervene in urban processes and their socio-spatial implications. In the Chinese context, relevant studies are still in their infancy, lacking comprehensive case-based analyses and coherent theoretical frameworks. Therefore, it is necessary to re-eval- uate platform urbanism from the perspective of shrinking cities and to systematically investigate its operational mechanisms and practical development pathways. This paper adopts a large language model (LLM)-assisted retrieval approach to systematically analyze platform-based practices in Chinese shrinking cities from 2020 to 2025. By employing multiple models to con- duct parallel searches across policy documents, media reports, and other online sources, and by integrating manual screening, deduplication, and cross-validation procedures, we constructed a database comprising 196 cases.

Large language models (LLMs) possess robust comprehensive capabilities for addressing complex problems and have increasingly been applied to better elucidate urban phenomena. Amid the surge of LLMs, there is an urgent need for urban researchers to understand how previous works have integrated LLMs across various disciplines. In this paper, we conduct a systematic review of 233 articles focusing on the application of LLMs in urban studies, analyzing the developing tendencies using information extracted from articles with the aid of a customized Generative Pre-trained Transformer (GPT) assistant and giving in-depth reviews across different subfields. The findings highlight an exponential growth in related research over the past six years, with LLMs being applied to diverse scenarios such as text analysis and generation, domain knowledge question-answering as well as field- related task. Besides, GPT-based and Bidirectional-Encoder-Representations-from-Transformers-based (BERT- based) have emerged as the two mostly used models, with embedding and fine-tuning being the predominant methods for data processing and model adaptation. Additionally, the paper also addresses common concerns about LLMs and identifies future research opportunities in urban studies. This comprehensive analysis aims to provide valuable insights for researchers exploring the application of LLMs in urban studies and for those who have yet to begin utilizing them in their research.

Robots are entering from factories an d laboratories into the urban space, to improve its smart governance and service, alleviate the agin g pressure, and promote sustainable and resilien t urban development. The application of urban robots has become an inevitable trend in the future development of cities. Like other disruptive technologies, its application will reshape urban life and urban space, but the existing research lacks a discussion on its relationship with urban space. Our research defines the concept of “urban robots” and constructs a feature analysis framework to describe the workflow of urban robots, covering its physical, social, and digital attributes, through a systematic literature review of 78 WoS core collectio n literatures. Based on the framework, this pape r further summarizes the characteristics of urban robots, six of their application areas as well as spatial problems they face such as diverse obstacles, lack of structural rules, and a high likelihood o f cross interference. Finally, in order to solve the spatial problems faced by urban robots and place some limits on their behaviors, this paper, based o n design cases, proposes exploratory strategies fo r urban space response and coordination, so as to promote thinking about future urban space design.

第四次工业革命背景下催生出的一系列新兴技术正在以肉眼可见的速度重塑着城市发展运行的逻辑与居民日常生活的场景 [1]。通过发挥人的需求与价值观、 服务场景模式以及空间功能形态的联动作用， 新兴技术促进当下城市迈入了崭新的发展阶段。 新的时代与技术背景也给城市治理带来诸多新的机遇与挑战。 因此， 科学理性地认知技术与城市多主体之间的关系进而引导未来技术发展与城市治理、 居民生活相互协调便显得至关重要。 技术与城市： 泛智慧城市技术提升城市韧性* 作者简介李伟健清华大学建筑学院华中科技大学建筑与城市规划学院龙瀛（通信作者） 清华大学建筑学院和恒隆房地产研究中心清华大学生态规划与绿色建筑教育部重点实验室研究员，博士生导师 2020年新冠肺炎疫情的暴发给中国乃至世界城市的发展运行以及人们的日常生活带来了巨大的冲击与影响 [2]。与17年前的SARS （严重急性呼吸综合征）时期相比， 新兴技术的迭代与发展给我们当下城市应对疫情的智慧化方法与手段带来了诸多影响。 因此， 本文进一步聚焦泛智慧城市的 10项代表性新兴技术， 并结合具体的案例进行分析阐述， 力求对其在新冠肺炎疫情期间发挥的作用有更加深入的了解与评估， 给未来社会各界应对类似的突发公共安全事件及日常城市治理带来更多 *基金项目： 本文受到国家自然科学基金面上项目（编号51778319） 、 重点项目（编号71834005） ； 清华大学自主科研计划和国家科技重大专项（编号2017ZX07103- 002）共同资助。 2020-vol2-4-26.indd 64 2020/4/26 16:03:31 公共卫生与规划响应 | 65 的启示与意义。 1 泛智慧城市技术的定义与应用概况智慧城市是数字城市之后信息化城市发展的一种高级形态 [3]， 但目前而言， 我国诸多智慧城市仍主要围绕智慧政务、 交通、 民生、 市政等各个方面的信息基础设施来进行建设或应用， 并强调大数据、 云计算、 物联网等新一代 ICT支持下的城市智能管理 [4]。 本文所关注的泛智慧城市技术并不局限于政府主导建设 “智慧城市”技术， 而更加偏向于被城市多元主体所使用， 服务于城市治理、 企业运行、 居民工作生活等多元维度的一系列新兴发展技术。 根据技术应用的广度与深度可将选取的 10项泛智慧城市技术划分为基础性通用技术与功能性应用技术。 基础性通用技术包含移动互联网、 物联网、 大数据、 云计算、 人工智能和区块链。 其中移动互联网和物联网将人与万物彼此信息互联， 实现实时感知与反馈的同时产生海量的时空大数据， 并可通过云计算对其进行高效存储与运算。 在此过程中， 人工智能得以辅助优化数据的算法与分析， 而区块链进一步保障了整合数据的安全透明与可靠。 功能性应用技术包含机器人与自动化系统、 智能建造、 虚拟现实/增强现实/混合现实以及共享经济。 其往往在基础性通用技术的支持下， 有更加聚焦的、 特定的功能与应用场景。 其中共享经济虽然严格意义上并不属于一种技术， 但也属于一种广泛应用且深刻影响城市发展与场景使用的创新模式， 因此被纳入功能性应用技术之一。 本文从官方媒体报道、 已发表论文以及微信公众号文章、 微博等公开信息平台进行系统性信息挖掘与素材整理， 并对政府/管理者、 医疗工作者、 公司企业、 公众群体这4类服务对象以及技术应用的出现时间进行结构化注记， 最终共整理得到200余条泛智慧城市技术的相关应用信息（见图1） 。 笔者将对其依次进行详细论述。

125 规划提高城市免疫力 Planning Improves City’s Immunity: A Written Conversation on COVID-19 BREAKOUT 和明确实施主体。第三，强化将政府主导的智慧城市建设理念与目前市场主导的“互联网+大数据”理念深度结合，打通数据与管理壁垒，开展面向广大公众的政务服务，并形成政府与公众互动的“共治共享”治理新局面，构建应急时期的“群防、群策与群控”治理体系与常态时期的 “公众参与”治理体系。 【作者简介】 周素红，中国城市规划学会理事。中山大学地理科学与规划学院教授、广东省公共安全与灾害工程技术研究中心主任。 【doi】10.11819/cpr20201623v 在当前技术塑造的“新”城市背景下，多方应对疫情的手段相比17年前的非典时期有着千差万别。笔者将以各种新兴技术为线索，观察和讨论泛智慧城市（即不囿于政府主导的智慧城市） 的不同技术在这次疫情应对过程中如何提高城市的韧性（弹性）。 一、大数据：不仅是对海量数据的应用， 更是对应着思维方式或城市与社会运行方式的改变。从疫情的实时查询、可视化、接触人员识别、分析预测，到辅助资源调度与防控决策，可以看到大数据已经成为居民生活、城市运行的重要参与媒介。 二、人工智能：其算法可以更好地将医疗资源、社会资源与城市空间相匹配。从辅助病毒分析、药物研发到智能识别医疗图像及公众体征， 人工智能技术大大提升了医疗工作的效率；智能外呼服务及疫情自助咨询服务则更加体现其“科技向善”、人性化关怀的一面。 三、移动互联网和云计算：移动通信技术的迭代使得大量日常事务得以线上运行，例如居家办公、线上教育、线上娱乐等，通过虚拟连接与空间隔离大幅提高了疫情时期公众居家生活的 “耐力”。咨询科普预约、物资供需匹配、疫情线索上报甚至是远程医疗会诊，也得以借助高速通信网络及应用生态平台发挥巨大效用。而云计算作为大规模线上业务运行的核心幕后支持，其弹性扩容能力也保证了春节和抗疫期间流量暴涨业务的正常运行。 四、传感网与物联网：不论是救灾物资的高效运输、医疗资源的追踪监管还是医疗环境、病患体征的智能感知监控，亦或是智能健康家居的布置，无不与传感设备及物联网技术密切相关。 随着应用成本的逐渐降低，万物互联将会成为可能，传感网与物联网或将成为未来应对疫情最核心的支持技术。 五、机器人与自动化系统：无人化趋势在本次抗疫过程中得以较多体现，如无人运营超市、 无接触式智能配送机器人、自动化消毒机器人、 导诊治疗机器人、巡航警示无人机等的出现，可以最大程度地降低交叉感染风险。 六、智能建造：在智能建造技术群（BIM建筑信息模型、装配式建筑技术等）的支持下，建筑基础设施的施工效率和精准度有着大幅度提升，为应急医院建设和设施提升提供充分保障。 七、虚拟现实/增强现实/混合现实：受到疫情影响更大的是城市空间，我们不能出门、不能逛街。而虚拟现实、增强现实、混合现实技术所体现出的沉浸式、交互性、多感知性和构想性特点，有望让人们把目光从实体空间转向虚拟空间，拓展居家生活的“活动”场景与范围。 八、共享经济：在应对疫情的过程中，共享经济作为对传统经济的补充，发挥了互助作用， 保证了一部分供需关系的建立。不同社会力量在运营的同时共享资源、共享服务、共享技术并具有风险共担的关怀，这种共享思维不仅仅在抗疫时期，在未来城市发展过程中也将发挥巨大的潜能与作用。

In the past decade, China has made great achievements in smart city development. Under the back- ground of the city transition and debt problem, China's smart city construction returns to rationality. Therefore, it is particularly important to clarify the characteristics and trends of China's smart city development in the future. The results showed that China attached great importance to simultaneous smart development in the process of new urbanization, and focused on the topdown promo - tion of smart life at the overall urban scale. In terms of smart city construction mode, the public-private coop - eration mode is the current mainstream, and the tripartite cooperation between the government, business and the public will be the important trend to promote the further development of smart city. Besides, China valued the establishment of data centers for the integration of urban system management and operation both at the vertical and horizontal levels .

目录主编寄语俞孔坚 / 警惕智能工具的陷阱论文龙瀛 / （新）城市科学：利用新数据、新方法和新技术研究“新”城市张昭希，龙瀛 / 穿戴式相机在研究个体行为与建成环境关系中的应用李复，常贺星 / 无人机测量在景观设计科研与实践中的应用韩依纹，张舒，殷利华 / 大都市区绿地碳储存能力及其空间分布特点探究：以韩国首尔市为例观点与评论姜斌 / 九问：浅论新科技对城市环境规划与设计的影响何宛余 / 竞争、并存与共赢—智能设计工具与人类设计师的关系埃米莉·施里克曼 / 走向远方：新工具与新技术在景观设计领域的应用测试罗亚丹 / 从交通基础设施到绿色基础设施—无人驾驶城市中的柔性未来道路主题实践蕾娜·约翰逊，法比奥·杜阿尔特，卡洛·拉蒂 / Roboat：阿姆斯特丹自动船系统王腾，茅明睿，崔博庶 / 规划设计智能化调研工具—“猫眼象限”调研分析系统的特点与应用刘祎绯，牟婷婷，黄子薇，哈日桂 / 北京什刹海金丝套滨水空间的视觉感知意象研究与眺望景观优化策略程娇华，沈振江 / 基于增强现实的规划支持工具：以建筑形态合规性检验为例探索与过程陆小璇 / 科技的人性化演进索尼娅·贝查尔特 / 坦桑尼亚农用无人机皮娅·弗里克 / 推进沉浸式数据交互的虚拟现实技术 4 8 22 38 55 66 76 84 92 100 112 121 132 144 146 153 主编俞孔坚 / 执行主编李迪华 / 执行副主编王志芳、李明翰、许立言 / 名誉编委程绪珂、崔愷、冯宗炜、何镜堂、蒋有绪、金鉴明、李文华、陆大道、马国馨、彭一刚、齐康、任南琪、吴良镛、张廷皓 / 国际编委杰克·埃亨、亨利·巴瓦、凯瑟琳·布尔、 加雷斯·多尔蒂、戴佛·加兹瓦达、克里斯蒂娜·希尔、伊丽莎白·K·梅尔、帕特里克·A·米勒、玛丽·帕多瓦、玛姬·罗、马里奥·谢赫南、安妮·惠斯顿·斯本、弗雷德里克·斯坦纳、卡尔·斯坦尼兹、安琪·施托克曼、罗伯特·L·塞耶 / 编委鲍家声、包满珠、包志毅、蔡强、车生泉、车伍、陈军、陈其兵、陈同滨、成玉宁、杜春兰、段进、樊杰、高翅、顾朝林、郭旃、韩林飞、韩西丽、洪铁城、李津逵、李树华、李炜民、李雄、林珲、刘滨谊、刘晖、刘克成、卢济威、吕斌、吕勤智、孟宪民、 欧阳志云、庞伟、邱建、邵健、宋文沛、谭徐明、汪芳、王浩、王建国、王澍、王向荣、王仰麟、吴文媛、吴志强、谢纯、许大为、杨保军、杨锐、叶强、余柏椿、于长江、张天新、赵辰、郑伟元、周志辉、朱育帆、宗跃光出版社 / 责任编辑张羽 / 地址北京市朝阳区惠新东街4号富盛大厦15层（100029） / 网址 journal.hep.com.cn / 电话 0086-10-5855 6485 / 编辑部 / 本期学术召集人龙瀛 / 编辑部主任佘依爽（兼本期内容编辑） / 责任编辑田乐 / 编辑汪默英、王颖、田晓劼、王胤瑜、萨拉·雅各布斯（兼） 、张健 （兼） / 探索与过程专栏编辑陆小璇 / 美术指导王江 / 美术编辑陈丽丽 / 海外编辑姜斌 / 地址北京市海淀区中关村北大街127-1号北大科技园303-3室（100080） / 电话 0086-10- 6274 7821 / 电子邮箱 lafrontiers@foxmail.com / 网站 www.

“人工智能”的出现大幅提升了人们的生产及生活效率，但与此同时，人类自身的就业环境也深受影响。那么，对于设计行业而言，人工智能又将带来怎样的挑战与机遇？由此，《景观设计学》邀请了6位来自建筑设计、城市规划、景观设计、工业设计等不同学科的学者、设计师，分别回答了什么是人工智能、人工智能可能对设计师的工作产生何种影响， 以及人工智能会创造什么样的生活方式三个问题。多数受访者认为，当前的人工智能并非真正意义上的人工智能，其不具备自我意识，亦无法完成创造性行为。而在参与设计工作时，人工智能虽然可以大幅减少设计师的程序性劳动，但由于其采用的是权重叠加和“去少存多”的数据处理方式，运算结果缺乏伦理性和价值评判，因而还远远无法胜任创造性工作。 而在未来，人工智能无疑会对人类的生活方式产生巨大影响，甚至远超出我们的想象。

Large-scale models are generally associated with large spatial modelling units, for example, counties or super grids (several to dozens of km 2). Few applied urban models can achieve a large spatial coverage with irregular spatial units due to data availability and computation load. The framework of automatic identification and characterization of blocks developed by Liu and Long (2016) makes such an ideal model possible by establishing the existing urban blocks using road networks and points of interest for very large areas (e.g., a country or a continent). In this study, we develop a mega-vector-blocks cellular automata model (MVB-CA) to simulate urban expansion at the block level for 654 Chinese cities. The existing urban blocks in 2012 were used for initiating the MVB-CA and are generated using multi-levelled road networks and ubiquitous points of interest. We then simulate block-based urban expansion of all the cities from 2012 to 2017. The national spatial development strategies of China are discussed extensively by academia and policy makers, while the baseline scenario and other simulated urban expansion scenarios have been tested and compared horizontally. As one of the first block-based urban expansion models at a national scale, its academic contributions, practical applications, and potential biases are also discussed in this paper. The developed MVB-CA using general approaches is also applicable for other counties.

Against the paucity of information on urban parcels in China, we propose a method to automatically identify and characterize parcels using OpenStreetMap (OSM) and points of interest (POI) data. Parcels are the basic spatial units for fine-scale urban modeling, urban studies, and spatial planning. Conventional methods for identification and characterization of parcels rely on remote sensing and field surveys, which are labor intensive and resource consuming. Poorly developed digital infrastructure, limited resources, and institutional barriers have all hampered the gathering and application of parcel data in China. Against this backdrop, we employ OSM road networks to identify parcel geometries and POI data to infer parcel characteristics. A vector-based cellular automata model is adopted to select urban parcels. The method is applied to the entire state of China and identifies 82 645 urban parcels in 297 cities. Notwithstanding all the caveats of open and/or crowd-sourced data, our approach can produce a reasonably good approximation of parcels identified using conventional methods, thus it has the potential to become a useful tool.

Here we sketch the rudiments of what constitutes a smart city which we define as a city in which ICT is merged with traditional infrastructures， coordinated and integrated using new digital technologies．We first sketch our vision defining seven goals which concern：developing a new understanding of urball problems；effective and feasible ways to coordinate urban technologies；models and methods for using urban data across spatial and temporal scales； developing new technologies for communication and dissemination；developing new forms of urban governance and organization；defining critical problems relating to cities，transport，and energy；and identifying risk，uncertainty，and hazards in the smart city．To this，we add six research challenges：to relate the infrastructure of smart cities to their operational functioning and planning through management，control and optimization；to explore the notion of the city as a laboratory for innovation；to provide portfolios of urban simulation which inform future designs；to develop technologies that ensure equity，fairness and realize a better quality of city life；to develop technologies that ensure informed participation and create shared knowledge for democratic city governance； and to ensure greater and more effective mobility and access to opportunities for urban populations．We begin by defining the state of the art，explaining the science of smart cities．We define six scenarios based on new cities badging themselves as smart，older cities regenerating themselves as smart，the development of science parks，tech cities，and technopoles focused on high technologies，the development of urban services using contemporary ICT，the use of ICT to develop new urban intelligence functions．and the development of online and mobile forms of participation．Seven project areas are then proposed： Integrated Databases for the Smart City，Sensing，Networking and the Impact of New SocialMedia，Modelling Network Performance，Mobility and Travel Behaviour，Modelling Urban Land Use，Transport and Economic Interactions，Modelling Urban Transactional Activities in Labor and Housing Markets， Decision Support as Urban Intelligence，Participatory Governance and Planning Structures for the Smart City．Finally we anticipate the paradigm shifts that will occur in this research and define a series of key demonstrators which we believe are important to progressing a science of smart cities． 关键词：智慧城市科学；信息通信技术；范式转换

Here we sketch the rudiments of what constitutes a smart city which we define as a city in which ICT is merged with traditional infrastructures, coordinated and integrated using new digital technologies. We first sketch our vision defining seven goals which concern: developing a new understanding of urban problems; effective and feasible ways to coordinate urban technologies; models and methods for using urban data across spatial and temporal scales; developing new technologies for communication and dissemination; developing new forms of urban governance and organization; defining critical problems relating to cities, transport, and energy; and identifying risk, uncertainty, and hazards in the smart city. To this, we add six research challenges: to relate the infrastructure of smart cities to their operational functioning and planning through management, control and optimization; to explore the notion of the city as a laboratory for innovation; to provide portfolios of urban simulation which inform future designs; to develop technologies that ensure equity, fairness and realize a better quality of city life; to develop technologies that ensure informed participation and create shared knowledge for democratic city governance; and to ensure greater and more effective mobility and access to opportunities for urban populations. We begin by defining the state of the art, explaining the science of smart cities. We define six scenarios based on new cities badging themselves as smart, older cities regenerating themselves as smart, the development of science parks, tech cities, and technopoles focused on high technologies, the development of urban services using contemporary ICT, the use of ICT to develop new urban intelligence functions, and the development of online and mobile forms of participation. Seven project areas are then proposed: Integrated Databases for the Smart City, Sensing, Networking and the Impact of New SocialMedia, Modelling Network Performance, Mobility and Travel Behaviour, Modelling Urban Land Use, Transport and Economic Interactions, Modelling Urban Transactional Activities in Labor and Housing Markets, Decision Support as Urban Intelligence, Participatory Governance and Planning Structures for the Smart City. Finally we anticipate the paradigm shifts that will occur in this research and define a series of key demonstrators which we believe are important to progressing a science of smart cities. 关键词 ： 智慧城市科学 ； 信息通信技术 ； 范式转换