Elements: Data: U-Cube: A Cyberinfrastructure for Unified and Ubiquitous Urban Canopy Parameterization

元素：数据：U-Cube：统一且无处不在的城市冠层参数化的网络基础设施

• 批准号: 1835739
• 负责人: Daniel Aliaga
• 金额: $ 60万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-01-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1835739&HistoricalAwards=false
• 关键词: Elements; Data; Cube; Cyberinfrastructure; Unified

Urban canopy parameters (UCPs) can be used in model simulations to study the health and behavior of a city, determine the ability to sustain a growing population, and study potential impacts of extreme weather events. The ability to identify and compute urban canopy parameters has been a missing element in city models; this project develops that capability for use in city design and analysis, integrating weather models and remote sensing data to infer a 3D model of cities of various sizes. The project deploys innovative science-based analysis tools within an extensible, broadly-available cyberinfrastructure portal, allowing users to ingest satellite imagery and other geographic information system (GIS) data to calculate urban canopy parameters. The cyberinfrastructure would improve urban modeling and planning, particularly for extreme weather events. The tools and high-performance computing and storage resources would be usable by other researchers through a portal. Potential beneficiaries include smaller and disadvantaged cities and countries without the resources for urban characterization and modeling necessary for such urban planning. There are also plans to transfer the results of this research to communities beyond college students -- to local teachers and secondary students and museums, and to the GIS urban planning user communities at local, state, and international levels.The project develops cyberinfrastructure which would use a novel inverse modeling approach incorporating satellite images, social science and urban zonal data, to infer a 3D model of a city from which urban canopy parameters could be derived for use in simulation models. The focus is on weather modeling, urban parameterization and a desire to better understand sustainable urbanization. The main cyberinfrastructure products will be 3D urban models and UCP values for urban locations. These UCP parameters will be used for fine-scale urban weather modeling, and evaluation of various classification techniques and simulation models in an integrated portal. The approach differs from prior work that relied on simple urban canopy models, either tuned for a large metropolis or assuming that all cities are the same. The team uses a cyberinfrastructure platform at Purdue (HubZERO) and the Geospatial Data Analysis Building Blocks (GABBs), a suite of software modules developed during a previously funded NSF Data Infrastructure project. The resulting platform can be deployed using Amazon Web Services, extending built-in geospatial data capabilities and providing a scalable CI solution. This platform can be used by researchers to test predictive models or deploy applications that have been developed. The team has cultivated relationships with the research communities and stakeholders relevant to the proposed research. Through the World Urban Database and Access Portal Tools (WUDAPT) project -- a community-based project to gather a census of cities around the world -- the team is already connected to the urban planning community globally. The project will improve urban weather modeling accuracy and increase availability of and access to the new techniques, capabilities and dedicated cyberinfrastructure. The results have the potential to support city officials and urban planners, especially in regions with the fastest rate of urbanization and/or those in developing countries, where access to computational resources is likely to be limited. This award by the NSF Office of Advanced Cyberinfrastructure will be jointly supported by the Division of Chemical, Bioengineering, Environmental, and Transport Systems, within the NSF Directorate for Engineering; and the Division of Atmospheric and Geospace Sciences and the Integrative and Collaborative Education and Research (ICER) Program, within the NSF Directorate for Geosciences.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

城市冠层参数（UCPs）可用于模型模拟研究城市的健康和行为，确定维持人口增长的能力，并研究极端天气事件的潜在影响。识别和计算城市冠层参数的能力一直是城市模型中缺失的元素；该项目开发了用于城市设计和分析的能力，整合天气模型和遥感数据，推断出不同规模城市的3D模型。该项目在一个可扩展的、广泛可用的网络基础设施门户中部署了创新的基于科学的分析工具，允许用户获取卫星图像和其他地理信息系统（GIS）数据，以计算城市冠层参数。网络基础设施将改善城市建模和规划，特别是针对极端天气事件。其他研究人员可以通过门户网站使用这些工具和高性能计算和存储资源。潜在的受益者包括规模较小和处境不利的城市和国家，这些国家没有资源进行这种城市规划所需的城市特征和建模。他们还计划将这项研究的结果转移到大学生以外的社区——当地教师、中学生和博物馆，以及地方、州和国际层面的GIS城市规划用户社区。该项目开发的网络基础设施将使用一种新型的逆建模方法，结合卫星图像、社会科学和城市区域数据，推断出一个城市的3D模型，从中可以推导出城市冠层参数，用于模拟模型。重点是天气建模、城市参数化和更好地理解可持续城市化的愿望。主要的网络基础设施产品将是3D城市模型和城市位置的UCP值。这些UCP参数将用于精细尺度的城市天气建模，以及综合门户中各种分类技术和模拟模型的评估。该方法不同于之前依赖于简单的城市冠层模型的工作，要么针对大城市进行调整，要么假设所有城市都是相同的。该团队使用普渡大学的网络基础设施平台（HubZERO）和地理空间数据分析构建块（gabb），这是一套软件模块，是在先前资助的国家科学基金会数据基础设施项目中开发的。生成的平台可以使用Amazon Web Services进行部署，扩展内置的地理空间数据功能，并提供可扩展的CI解决方案。研究人员可以使用该平台来测试预测模型或部署已开发的应用程序。该团队已与研究团体和与拟议研究相关的利益相关者建立了关系。通过世界城市数据库和访问门户工具（WUDAPT）项目（一个以社区为基础的项目，收集世界各地城市的人口普查），该团队已经与全球城市规划界建立了联系。该项目将提高城市天气建模的准确性，增加新技术、能力和专用网络基础设施的可用性和可及性。研究结果有可能为城市官员和城市规划者提供支持，特别是在城市化速度最快的地区和/或发展中国家，这些地区获得计算资源的机会可能有限。该奖项由NSF高级网络基础设施办公室颁发，将由NSF工程局下属的化学、生物工程、环境和运输系统部门联合支持；大气和地球空间科学部和综合协作教育与研究（ICER）计划，隶属于美国国家科学基金会地球科学理事会。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Synthesis and Completion of Facades from Satellite Imagery

卫星图像的外立面合成和完成

• DOI: 10.1007/978-3-030-58536-5_34
• 发表时间: 2020
• 期刊: European Conference on Computer Vision
• 作者: Zhang, X.;May, C.;Aliaga, D.
• 通讯作者: Aliaga, D.

Tree Instance Segmentation with Temporal Contour Graph

• DOI: 10.1109/cvpr52729.2023.00218
• 发表时间: 2023-06
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: A. Firoze;Cameron Wingren;Raymond A. Yeh;Bedrich Benes;Daniel G. Aliaga

An output-driven approach to design a swarming model for architectural indoor environments

一种输出驱动的方法来设计建筑室内环境的集群模型

• DOI: 10.1016/j.cag.2020.02.003
• 发表时间: 2020
• 期刊: Computers graphics
• 作者: Mathew, T.;Benes, B.;Aliaga, D.
• 通讯作者: Aliaga, D.

Design and Deployment of Photo2Building: A Cloud-based Procedural Modeling Tool as a Service

Photo2Building 的设计和部署：基于云的程序建模工具即服务

• DOI: 10.1145/3311790.3396670
• 发表时间: 2020
• 期刊: PEARC '20: Practice and Experience in Advanced Research Computing
• 作者: Bhatt, M.;Kalyanam, R.;Nishida, G.;He, L.;May, C.;Niyogi, D.;Aliaga, D.
• 通讯作者: Aliaga, D.

Urban tree generator: spatio-temporal and generative deep learning for urban tree localization and modeling

• DOI: 10.1007/s00371-022-02526-x
• 发表时间: 2022-06
• 期刊: The Visual Computer
• 作者: A. Firoze;Bedrich Benes;Daniel G. Aliaga