RAPID: COVID-19 Response Support: Building Synthetic Multi-scale Networks

RAPID：COVID-19 响应支持：构建综合多尺度网络

• 批准号: 2027541
• 负责人: Madhav Marathe
• 金额: $ 17.36万
• 依托单位: University of Virginia Main Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027541&HistoricalAwards=false
• 关键词: RAPID; COVID; 19; Response; Support

The Novel 2019 Coronavirus (COVID-19) has already caused unprecedented global social, economic, and health impact. This project will develop synthetic global multi-scale social contact networks. The synthetic but realistic social contact networks can capture human interactions either at an individual or community level. The networks can be used in conjunction with agent-based models to simulate the ongoing COVID-19 pandemic. The simulations can in-turn be used to design and assess various interventions that balance health benefits with social and economic costs. Data will be made available to the scientific community. The PIs will also work with other research groups and continue their partnership with other federal and state agencies to support their response efforts. Developing synthetic social contact networks is a statistically and algorithmically challenging problem. This project will synthesize ensembles of two classes of synthetic social contact networks -- patch-based meta-population networks and individualized synthetic social contact populations and networks using a combination of machine learning and data driven modeling techniques. The need for such data driven mechanistic modeling methods has become abundantly clear in regimes when the available data is sparse and noisy. The project will undertake a detailed statistical analysis of the algorithms and the synthetic networks they produce. This includes methods to conduct global sensitivity analysis and methods to quantify the uncertainty in the outcomes as a function of the network structure. One of the many uses of this resource, is to support individual-based as well as meta-population-based simulation models for epidemic spread in general, and COVID-19 in particular. Beyond supporting ongoing COVID-19 outbreaks, these synthetic social contact networks will be useful in responding to other epidemics. The PIs plan to make this data available to the global research community so that researchers around the world can immediately use it to assess the pandemic and the response efforts in their respective regions.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.

新型2019冠状病毒（COVID-19）已经对全球社会、经济和健康造成了前所未有的影响。该项目将开发合成的全球多尺度社会联系网络。合成但现实的社会联系网络可以在个人或社区层面上捕捉人类互动。该网络可与基于代理的模型结合使用，以模拟正在进行的COVID-19大流行。这些模拟又可用于设计和评估各种干预措施，以平衡健康效益与社会和经济成本。数据将提供给科学界。PI还将与其他研究小组合作，并继续与其他联邦和州机构合作，以支持他们的应对工作。 开发合成的社会联系网络是一个统计和算法上具有挑战性的问题。该项目将综合两类合成社会联系网络的集合-基于补丁的元人口网络和个性化的合成社会联系人口和网络，使用机器学习和数据驱动的建模技术相结合。在可用数据稀疏且有噪声的情况下，对这种数据驱动的机械建模方法的需求已经变得非常清楚。该项目将对算法及其产生的合成网络进行详细的统计分析。这包括进行全球敏感性分析的方法和将结果的不确定性量化为网络结构的函数的方法。该资源的众多用途之一是支持基于个人以及基于元人群的流行病传播模拟模型，特别是COVID-19。 除了支持持续的COVID-19爆发外，这些合成社交联系网络将有助于应对其他流行病。PI计划将这些数据提供给全球研究界，以便世界各地的研究人员可以立即使用这些数据来评估流行病及其各自地区的应对工作。该奖项反映了NSF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

High resolution proximity statistics as early warning for US universities reopening during COVID-19

高分辨率邻近统计数据作为美国大学在 COVID-19 期间重新开放的预警

• 发表时间: 2020
• 期刊: medRxiv
• 作者: Mehrab, Z;Ranga, AG;Sarkar, D;Venkatramanan, S;Baek, Y;Swarup, S;Marathe, M
• 通讯作者: Marathe, M

Using Active Queries to Infer Symmetric Node Functions of Graph Dynamical Systems

• 发表时间: 2022
• 期刊: J. Mach. Learn. Res.
• 作者: Abhijin Adiga;C. Kuhlman;M. Marathe;Sujith Ravi;D. Rosenkrantz;R. Stearns

Cohorting to isolate asymptomatic spreaders: An agent-based simulation study on the Mumbai Suburban Railway

• DOI: 10.5555/3463952.3464199
• 发表时间: 2020-12
• 期刊: ArXiv
• 作者: A. Talekar;S. Shriram;N. Vaidhiyan;G. Aggarwal;Jiangzhuo Chen;S. Venkatramanan;Lijing Wang;A. Adiga;A. Sadilek;A. Tendulkar;M. Marathe;R. Sundaresan;M. Tambe

Phase-Informed Bayesian Ensemble Models Improve Performance of COVID-19 Forecasts

阶段信息贝叶斯集成模型提高了 COVID-19 预测的性能

• DOI: 10.1609/aaai.v37i13.26855
• 发表时间: 2023
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Adiga, Aniruddha;Kaur, Gursharn;Wang, Lijing;Hurt, Benjamin;Porebski, Przemyslaw;Venkatramanan, Srinivasan;Lewis, Bryan;Marathe, Madhav V.
• 通讯作者: Marathe, Madhav V.

Data-Driven Real-Time Strategic Placement of Mobile Vaccine Distribution Sites

• DOI: 10.1101/2021.12.15.21267736
• 发表时间: 2021-12
• 作者: Z. Mehrab;M. Wilson;S. Chang;G. Harrison;B. Lewis;A. Telionis;J. Crow;D. Kim;S. Spillmann;K. Peters;J. Leskovec;M. Marathe