Phase II I/UCRC [George Mason University]: Center for Spatiotemporal Thinking, Computing and Applications.

II 期 I/UCRC [乔治梅森大学]：时空思维、计算和应用中心。

• 批准号: 1841520
• 负责人: Chaowei Yang
• 金额: $ 75万
• 依托单位: George Mason University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-03-15 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1841520&HistoricalAwards=false
• 关键词: Phase; II; UCRC; George; Mason

We live in a four dimensional world with three spatial dimensions and one temporal dimension. Understanding the nature of the spatiotemporal dimensions integratively will help us better prepare for challenges facing us in the 21st century and beyond: a) responding to climate change with better climate simulations, b) mitigating asteroids' impact to our home planet like the dinosaur-killer, c) resolving political disputations with spatiotemporal understanding of the culture, boundaries, history, and future of relevant nations, and d) equipping our future leaders with spatiotemporal thinking capability and decision support tools. Following the success of Phase I spatiotemporal Industry-University Cooperative Research Center (IUCRC) investigation as a collaboration among George Mason, Harvard, and the University of California-Santa Barbara, the second phase of the center will move forward with the mission to 1) build a national and international spatiotemporal infrastructure; 2) develop, with industry and agency members, new spatiotemporal technologies, solutions, tools, and software that will be easily integrated with existing and future industry products and services; 3) improve human intelligence by developing a set of spatiotemporal thinking methodologies built into K-16 curriculum; and 4) improving human capabilities in responding to grand scientific and engineering challenges. Outreach will be conducted to maximize the broader impacts: 1) collaborating closely with more than four active members each year to develop relevant methodologies and technologies; 2) disseminating research results to industry and government agency members and through publications for adoption and broader impacts. 3) working with leading associations to broadcast the research results and recruit new members; 4) developing new course material and curriculum within existing degree programs and broadcast for wider adoption; 5) continuing our diverse traditions to include minorities and other underrepresented groups in this STEM field; 6) making all results open source to benefit relevant domains nationally and internationally. The center will post all information on an official website (https://www.stcenter.net/) and two content management portals accessible through the official website. A project management website will be utilized to share all project reports, working papers, presentations, posters, and publications. The data and research results produced will be integrated into the center's operational community cloud (http://sites.cloud.gmu.edu/sthcp/index.php) to be maintained as a sustainable resource for the center for long term sustainability. Source code developed in the center will be open to the public using github.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.

我们生活在一个有三个空间维度和一个时间维度的四维世界。综合理解时空维度的本质，将有助于我们更好地应对21世纪及以后面临的挑战：A)通过更好的气候模拟来应对气候变化；b)减轻小行星对我们的家园星球的影响，就像恐龙杀手一样；c)通过对相关国家的文化、边界、历史和未来的时空理解来解决政治争端；d)为我们未来的领导人提供时空思维能力和决策支持工具。继乔治梅森大学、哈佛大学和加州大学圣巴巴拉分校合作开展的第一阶段时空产学研合作研究中心（IUCRC）取得成功之后，该中心第二阶段将继续推进以下任务：1)建立国家和国际时空基础设施；2)与行业和机构成员一起开发新的时空技术、解决方案、工具和软件，这些技术、解决方案和软件将很容易与现有和未来的行业产品和服务集成；3)通过开发一套嵌入K-16课程的时空思维方法来提高人类智力；4)提高人类应对重大科学和工程挑战的能力。将开展外展活动，以最大限度地发挥更广泛的影响：1)每年与四个以上的活跃成员密切合作，开发相关的方法和技术；2)向行业和政府机构成员传播研究成果，并通过出版物进行采用和广泛影响。3)与主要协会合作，宣传研究成果，招募新会员；4)在现有的学位课程中开发新的课程材料和课程，并进行广播，以供更广泛的采用；5)继续我们的多元化传统，将少数民族和其他未被充分代表的群体纳入STEM领域；6)使所有结果开源，以使国内和国际相关领域受益。中心将在官方网站（https://www.stcenter.net/）和通过官方网站访问的两个内容管理门户网站上公布所有信息。项目管理网站将用于共享所有项目报告、工作底稿、演示文稿、海报和出版物。所产生的数据和研究成果将整合到中心的运营社区云（http://sites.cloud.gmu.edu/sthcp/index.php）中，作为中心长期可持续发展的可持续资源进行维护。该中心开发的源代码将通过github向公众开放。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

Saliency-Regularized Deep Multi-Task Learning

• DOI: 10.1145/3534678.3539442
• 发表时间: 2022-07
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Guangji Bai;Liang Zhao

Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer model

使用 SpatioTemporal Transformer 模型预测野火多发地区每小时 PM2.5 浓度

• DOI: 10.1016/j.scitotenv.2022.160446
• 发表时间: 2023
• 期刊: Science of The Total Environment
• 影响因子: 9.8
• 作者: Yu, Manzhu;Masrur, Arif;Blaszczak-Boxe, Christopher
• 通讯作者: Blaszczak-Boxe, Christopher

Time series clustering in linear time complexity

• DOI: 10.1007/s10618-021-00798-w
• 发表时间: 2021-09
• 期刊: Data Mining and Knowledge Discovery
• 影响因子: 4.8
• 作者: Xiaosheng Li;Jessica Lin;Liang Zhao

Toward Model Parallelism for Deep Neural Network based on Gradient-free ADMM Framework

• DOI: 10.1109/icdm50108.2020.00068
• 发表时间: 2020-09
• 期刊: 2020 IEEE International Conference on Data Mining (ICDM)
• 作者: Junxiang Wang;Zheng Chai;Yue Cheng;Liang Zhao

FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data

• 发表时间: 2020-10
• 期刊: ArXiv
• 作者: Zheng Chai;Yujing Chen;Liang Zhao;Yue Cheng;H. Rangwala