Research Lab,
我们的城市是一个高度复杂的系统。面对日益交织的社会、生态与技术挑战，仅凭直觉难以识别其深层结构与运行逻辑。研究实验室致力于打造一个以数据分析与人工智能为核心的研究平台，专注于城市的感知、诊断与决策支持，推动从表象观察走向结构性理解，并以此为基础提供策略性的响应路径。
Our cities are highly complex systems. In the face of increasingly intertwined social, ecological, and technological challenges, intuition alone is no longer sufficient to grasp their underlying structures and operational logic. The Research Lab is committed to building a research platform centered on data analytics and artificial intelligence, focusing on urban sensing, diagnosis, and decision-making support. It aims to shift design thinking from surface-level observation to structural understanding, forming the basis for strategic responses.
任务 I Mission:
回应当代城市议题的复杂性挑战，研究实验室以人工智能与数据驱动方法为工具，推动设计者与研究者超越直觉与经验，建立基于证据的城市洞察与应对机制。
In response to the complexity of contemporary urban challenges, the Research Lab adopts AI and data-driven methodologies to empower designers and researchers to move beyond intuition and experience—establishing evidence-based insights and response mechanisms for the city.
核心组成 I Core Components:
Research Lab 的核心板块包括四大部分：
1.系统研究路径构建：
引导学员掌握从数据采集、处理、分析到洞察生成的完整研究流程；
2.关键议题聚焦实践：
围绕空间结构识别、环境绩效评估、行为建模与公平性分析等主题，结合真实案例开展实践训练；
3.跨学科协作机制：
提供导师指导与团队合作支持，构建具有研究深度与设计逻辑的项目支撑系统；
4.学术产出支持体系：
围绕学员的研究方向提供全流程指导，提升成果的学术转化率，支持论文辅导、展览策划与项目提案的孵化，助力获得出版与资助机会。
the four Core Components of Research Lab are:
1) Systematic Research Pathway: guiding participants through the full research pipeline—from data collection and processing to analysis and insight generation.
2) Practice-Oriented Thematic Focus: engaging real-world cases to explore key topics such as spatial structure identification, environmental performance evaluation, behavioral modeling, and urban equity analysis.
3) Cross-Disciplinary Collaboration: providing mentorship and team-based support to help participants develop research depth and design logic through collaborative projects.
4) Academic Output Support System: offering end-to-end guidance aligned with each participant's research direction, enhancing academic transformation through writing support, exhibition planning, and project proposal incubation—ultimately facilitating publication and funding opportunities.
实验室主任 | Lab Director
哈佛大学，GSD研究员
UCSB，地理科学博士在读
(城市数据科学与人工智能方向）
擅长领域：
机器学习 · 深度学习 · 强化学习 · 城市数据科学 · 交通预测 · 图像识别 · 遥感
研究经历:
Houpu Li 是一位建筑学与数据科学跨界融合的研究者，在加入哈佛大学之前，Li 曾在中国拥有近十年的建筑学研究与实践经验，涵盖教学、设计与城市项目策划等多个领域。现任哈佛大学GSD Values in the Built Environment（ViBE Lab）研究员，并在加州大学圣塔芭芭拉（UCSB）攻读“城市数据科学与人工智能专业" 博士学位，专注于空间数据科学、GeoAI 与复杂城市系统的优化设计。
他的研究将城市问题量化，并运用机器学习与空间分析方法为城市资源配置提供更公平与高效的解决方案并为城市设计/规划提供决策支持。在 哈佛大学的ViBE Lab，Li 深度参与城市住房评估与模拟平台的算法开发工作，致力于将数据工具转化为公共政策与空间设计之间的桥梁。
作为一名拥有丰富建筑竞赛经验和数据分析与开发背景的研究者，Li曾在康奈尔大学的Urban Data Research Lab担任研究助理，负责利用大数据、遥感技术和空间建模，深入分析城市的空间结构、交通模式和人类行为，提供数据驱动的解决方案以应对日益严峻的城市扩张、交通拥堵和环境挑战。同时，Li也是康奈尔大学MRP“ Urban data science课程” 的特邀讲师。
Research Associate at Harvard GSD
Ph.D. Student in Geography at UC Santa Barbara (Specializing in Urban Data Science and Artificial Intelligence)
Expertise:
Machine Learning · Deep Learning · Reinforcement Learning · Urban Data Science · Transportation Prediction · Computer Vision · Remote Sensing
Research Experience:
Houpu Li is a cross-disciplinary researcher at the intersection of architecture and data science. Before joining Harvard University, he had nearly a decade of experience in China in architectural research and practice, spanning teaching, design, and urban project planning. He is currently a research fellow at the Values in the Built Environment (ViBE) Lab at Harvard Graduate School of Design (GSD), and a Ph.D. student in the Geography Department at the University of California, Santa Barbara (UCSB), focusing on spatial data science, GeoAI, and the optimization of complex urban systems.
His research quantifies urban problems and applies machine learning and spatial analysis to improve the fairness and efficiency of urban resource allocation, while supporting evidence-based urban planning and design. At Harvard’s ViBE Lab, Li is deeply involved in the algorithm development of a city-scale housing assessment and simulation platform, aiming to bridge data tools with public policy and spatial design.
With a strong background in architectural competitions and data analysis, Li previously served as a research assistant at the Urban Data Research Lab at Cornell University, where he used big data, remote sensing, and spatial modeling to analyze urban form, transportation patterns, and human behavior. His work offers data-driven solutions to challenges such as urban sprawl, traffic congestion, and environmental stress. Li has also been invited as a guest lecturer for the “Urban Data Science” course in the MRP program at Cornell University.
实验室主任 | Lab Director
英属哥伦比亚大学（UBC），博士后
康奈尔大学，建筑与城市规划学院讲师
康奈尔大学，城市规划博士
(城市形态与动态感知方向)
擅长领域：
城市空间画像 · 多中心识别与城市结构演化 · 热岛效应分析 · 遥感与GIS融合建模 · GeoAI与政策效应模拟
研究经历：
Wenzheng Li 目前在康奈尔大学担任地理空间系统（GIS）与城市人工智能（Urban AI）数据科学方向的讲师，致力于探索人工智能技术在城市系统分析中的深度应用。他的研究紧密结合空间数据科学、遥感、AI建模与计量经济学，聚焦于城市形态演化、多中心结构识别、城市热岛效应分析与区域发展不平衡问题等关键议题。
Li 曾参与由美国联邦交通管理局（FTA）与共享使用移动中心（SUMC）**资助的“移动即服务（MaaS）”试点项目，探索如何利用城市交通数据优化出行选择，提升城市交通系统的响应性与公平性。
当前，Li 运用深度学习与图像识别技术，开展城市“画像建模”研究：包括从卫星影像、街景图像与遥感数据中识别城市的中心性结构、功能区演化、建成环境密度特征，进一步分析其对交通效率、居住环境与气候影响（如城市热岛）的空间响应机制。他特别关注单中心—多中心转型过程中对区域经济差异、生活质量和环境可持续性的影响，并通过引入AI算法动态评估这些结构变化背后的空间机制。
Postdoctoral Fellow, University of British Columbia (UBC)
Lecturer, College of Architecture, Art, and Planning, Cornell University
Ph.D. in Urban Planning, Cornell University
(Specializing in Urban Simulation and Dynamic Sensing)
Expertise:
Urban Spatial Profiling · Polycentricity and Urban Structural Evolution · Urban Heat Island Analysis · Integrated Remote Sensing and GIS Modeling · GeoAI and Policy Impact Simulation.
Research Experience:
Wenzheng Li is currently a lecturer in Geospatial Systems (GIS) and Urban Artificial Intelligence (Urban AI) at Cornell University, where his work explores the application of AI technologies in urban systems analysis. His research integrates spatial data science, remote sensing, AI modeling, and econometrics, with a focus on key issues such as urban form evolution, polycentric structure identification, urban heat island analysis, and regional development disparities.
Li contributed to a Mobility-as-a-Service (MaaS) pilot funded by the U.S. FTA and SUMC, using urban mobility data to optimize transportation systems.
Currently, he researches urban profile modeling with deep learning, analyzing satellite, street-view, and remote sensing data to identify urban structures, functional transitions, and density patterns. His work explores how these factors impact transport efficiency, living conditions, and climate effects (e.g., heat islands). He investigates polycentric urban transformation and its effects on economic disparities, quality of life, and sustainability, using AI to assess spatial dynamics.
W
2024-2025年，SCI Q1 已发表7篇
“粗糙断层上慢滑移事件的传播：聚集、反向传播与重复破裂”，《地球物理研究期刊：固体地球》，2025
Sun, Yudong, and Camilla Cattania. "Propagation of slow slip events on rough faults: Clustering, back propagation,
and re‐rupturing." Journal of Geophysical Research: Solid Earth 130.2 (2025): e2024JB029384.
”道路使用者的种族构成、交通罚单与警察拦截“，发表于《美国国家科学院院刊》，2024 W. Xu, M. Smart, N. Tilahun, S. Askari, Z. Dennis, H. Li, & D. Levinson, The racial composition of road users, traffic citations,
and police stops, Proc. Natl. Acad. Sci. U.S.A. 121 (24) e2402547121, 2024).
“多中心城市发展是否能够兼顾经济增长与区域公平？基于德国地区的多尺度实证分析”，
发表于《环境与规划A期刊》，2024
W. Li, S. Schmidt, S. Siedentop, Can polycentric urban development simultaneously achieve both economic growth and
regional equity? A multi-scale analysis of German regions,
Environment and Planning A: Economy and Space 56 (2), 525–545, 2024.
“规划制度与城市空间格局：基于跨国数据的比较研究”，发表于《规划教育与研究》，2024
S. Schmidt, W. Li, J. Carruthers, S. Siedentop, Planning institutions and urban spatial patterns: Evidence from a cross-national
analysis, Journal of Planning Education and Research 44 (3), 1186–1197, 2024.
“空间格局能否缓解城市热岛效应？来自德国大都市区的实证证据”，发表于《环境与规划B期刊》，2024
W. Li, S. Schmidt, Can spatial patterns mitigate the urban heat island effect? Evidence from German metropolitan regions,
Environment and Planning B: Urban Analytics and City Science 51 (8), 1948–1964, 2024.
“地方依恋、区域认同与坦桑尼亚莫希城市化的感知”，发表于《国际人居期刊》，2024
S. Schmidt, S. Nuhu, R. Thomas, W. Li, Place attachment, regional identity and perceptions of urbanization in Moshi, Tanzania,
Habitat International 150, 103132, 2024.
“中国城市发展格局的时空演化：动态与机制解读”，发表于《增长与变迁》，2024
W. Li, S. Schmidt, The spatial-temporal evolution of urban development patterns in Chinese cities: Dynamics and interpretations,
Growth and Change 55 (2), e12722, 2024.
“远程工作机会的行业分布对地区收入不平等的影响”，康奈尔大学图书馆收录，2024
H. Li, The Impact of Industry Distribution of Remote Work Opportunities on Regional Income Inequality?,
Cornell Univ. Library, 2024.
“基于强化学习的地震后住房恢复实时调度方法”，正在进行
Q. Yu, I. Alisjahbana, & V. W. H. Wong, Real-time adaptive scheduling of post-earthquake housing recovery using reinforcement learning, Proc. Assoc.
Collegiate Schools of Planning Conf., Minneapolis, MN, United States, (On the Wrinting Process)
“美国大城市兴趣点的空间布局如何塑造种族分离格局”, 正在进行
H.Li，W. Xu, W.Z, How the Spatial Configuration of Points of Interest Shapes Patterns of Racial Segregation in Major U.S. Cities
(On the Wrinting Process)
“标准化土地使用规范与地块可开发性建模：以达拉斯-沃斯堡地区的一个空间数据框架”, 正在进行
H.Li, Kamryn Mansfield, Carole Voulgaris.Standardizing Zoning Specifications and Modeling Parcel Developability: A Geospatial
Framework for the Dallas–Fort Worth Region， (Reviewed by Environmental Plannig B)
“基于Python的ZonePy程序包开发：一个用于标准化土地使用规范与可开发性
分析的空间建模程序包”, 正在进行
H.Li, Kamryn Mansfield, Carole Voulgaris.ZonePy and Zoner: A Spatial Modeling Toolkit for Standardizing Zoning and Analyzing
Parcel Developability， (Reviewed by Computers, Environment and Urban Systems)
实验室项目分享2024-2025 | Lab Project Showcase
项目一：
Project 1:
“Parcel Edge Classification Toolkit（PECT）：基于 Python 的场地边界分类与退界约束的可建设边界智能识别工具包开发“ | 2025Parcel Edge Classification Toolkit (PECT): A Python-based Toolkit for Parcel Edge Classification and Parcel Buildable Area Generation Based on the Zoning Setback Constraints | 2025
为解决传统场地可建设区域依赖人工标注、重复性高、效率低的问题，我们开发了 PECT ——一套结合城市用地规范的可建设区域自动生成工具包。该工具基于道路接邻关系与退界规则（如前退、后退、侧退及角地限制等），对地块边界进行智能分类，并自动生成符合当前规范的可建设边界。PECT 可广泛应用于城市设计、可开发性评估与参数化规划任务，显著提升空间设计流程中的规则嵌入能力与数据智能水平。
To address the inefficiencies of manually identifying buildable areas—often repetitive, time-consuming, and error-prone—we developed PECT, a toolkit for the automated generation of buildable zones based on urban land use regulations. Leveraging street adjacency and setback rules (such as front, rear, side, and corner constraints), PECT intelligently classifies parcel edges and generates boundary lines that comply with current zoning constraints. It is applicable to urban design, developability assessment, and parametric planning tasks, significantly enhancing the integration of regulatory logic and data intelligence within spatial design workflows.
项目二：
Project 2:
“基于 Python 的城市多中心结构自动识别与形态测度可视化工具包开发” | 2024
A Python-Based Automated Tool developing for Identifying and Measuring Urban Polycentric Morphology | 2024
为解决传统城市空间结构识别中存在的效率低、主观性强等问题，我们开发了一套基于 Python 的自动化程序，能够对城市的单中心与多中心结构进行形态测度，并将分析结果转化为可视化图像产品。该工具融合空间聚类、密度分析与多尺度指标体系，实现了从数据导入、结构识别到结果输出的全流程自动化，显著提升了城市形态研究的效率与客观性。
To address the low efficiency and subjectivity of traditional urban spatial structure analysis, we developed a Python-based automated program for measuring monocentric and polycentric urban forms, with outputs rendered as visual image products. Integrating spatial clustering, density analysis, and a multi-scale indicator system, the tool enables a fully automated workflow—from data import and structural identification to result visualization—significantly improving the efficiency and objectivity of urban morphology research.
项目三：
Project 3:
”基于 Python 的 Web 可视化平台开发：纽约曼哈顿 Uber 行驶轨迹、密度与交通拥堵的可视化“ | 2024Python-Based Web Map Platform: Visualizing Uber Trajectories, Density, and Traffic Congestion in Manhattan | 2024
为更直观理解城市出行模式与交通拥堵空间特征，我们构建了一个基于 Python 的 Web 地图叙事平台，从不同维度对纽约曼哈顿岛的 Uber 行驶数据进行可视化分析。项目聚焦于行驶轨迹、密度分布与拥堵程度等核心变量，通过轨迹数据处理、空间聚类与地图渲染，将城市交通动态转化为可交互的图像叙事，辅助分析交通热点与结构性瓶颈，并探索其与城市空间形态的关联。
To better understand urban mobility patterns and the spatial characteristics of traffic congestion, we developed a Python-based web map narrative platform that visualizes Uber trip data in Manhattan, New York. Focusing on key variables such as trip trajectories, spatial density, and congestion levels, the project integrates trajectory preprocessing, spatial clustering, and web-based map rendering to transform raw mobility data into interactive visual narratives. It supports the identification of traffic hotspots and structural bottlenecks, while revealing their spatial relationships with urban form.
项目四：
Project 4:
“基于 Mapbox GL 的 Web 地图叙事：纽约曼哈顿岛洪水风险与住房类型影响关系“ | 2024
Web Map Narrative with Mapbox GL: Visualizing the Relationship Between Flood Risk and Housing Types in Manhattan | 2024
为更直观理解纽约曼哈顿岛洪水风险等级与住房类型之间的空间关联，我们基于机器学习模型预测了 2020、2050 与 2100 年 100 年一遇洪水的空间分布，并构建了一个基于 Mapbox GL 的 Web 地图叙事平台。该平台将不同年份的洪水风险等级与住宅类型数据进行可视化叠加，揭示高风险区域与特定住房形式之间的暴露关系。通过交互式图层设计，用户可自主探索不同区域的脆弱性空间格局，为公平性导向的城市适应与气候韧性策略提供直观支持与空间参考。
To better understand the spatial relationship between flood risk levels and housing types in Manhattan, New York, we used machine learning models to predict the extent of 100-year flood events for the years 2020, 2050, and 2100. Based on these predictions, we developed a web-based map narrative platform using Mapbox GL. The platform overlays flood risk projections with housing type data, visualizing exposure patterns between high-risk areas and specific residential forms. Through interactive map layers, users can explore spatial vulnerability dynamics, providing intuitive support for equity-oriented urban adaptation and climate resilience strategies.
项目五：
Project 5:
“融合遥感影像与计算机视觉算法的非洲城市大尺度用地类型识别分析“ | 2024
Large-Scale Urban Land Cover Classification in African Cities Using Remote Sensing and Computer Vision | 2024
为填补非洲城市缺乏统一、高分辨率土地利用数据的现状，我们基于遥感影像与机器学习方法，对非洲592座城市的用地类型识别研究。项目融合多源卫星影像与分类算法，自动识别居住、工业、商业、绿地等主要城市功能区，并对其空间分布格局进行量化分析与可视化表达。该成果为区域尺度的城市规划、土地管理与资源优化配置提供了基础数据支持与空间决策依据。
To address the lack of consistent, high-resolution land use data across African cities, we conducted a large-scale land use classification study for 592 cities using remote sensing imagery and machine learning techniques. By integrating multi-source satellite data with supervised classification algorithms, the project automatically identifies major urban land use types—including residential, industrial, commercial, and green spaces—and analyzes their spatial distribution through quantitative and visual approaches. The results offer foundational data support for urban planning, land management, and resource allocation at the regional scale.
项目六：
Project 6:
“Grasshopper + GenAI 驱动的参数化设计工作流实践“ | 2024
Intelligent Parametric Design Workflow Driven by Grasshopper and Generative AI | 2024
为突破传统建模在策略生成与形式演化中存在的大量重复性操作与“不可回退”的逻辑限制，我们探索并实践了一套融合 Grasshopper 参数建模 与 生成式人工智能（GenAI） 的参数化设计工作流。该流程通过在 Grasshopper 中构建可调控的参数结构，并结合文本与图像生成工具，辅助生成初步空间原型。项目聚焦于算法生形在高级空间建模中的应用，并利用 Stable Diffusion 与 ComfyUI 作为创意参考机制，增强方案的发散性与表现力，为概念设计与竞赛策略提供高效支持。
To address the repetitive operations and irreversible logic often found in traditional modeling workflows, this project explores a design process that integrates Grasshopper-based parametric modeling with Generative AI (GenAI). The workflow constructs flexible parametric structures in Grasshopper and incorporates text-to-image tools to assist in generating early-stage spatial prototypes. It focuses on applying algorithmic form-finding to support advanced spatial modeling, while leveraging Stable Diffusion and ComfyUI as creative reference mechanisms—enhancing design divergence, visual expressiveness, and efficiency in conceptual design and competition scenarios.