RAPID: Using location-based big-data to model people's mobility patterns during the COVID-19 outbreak

RAPID：使用基于位置的大数据对 COVID-19 爆发期间人们的流动模式进行建模

• 批准号: 2027412
• 负责人: Kathleen Stewart
• 金额: $ 8.21万
• 依托单位: University of Maryland, College Park
• 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: 2020-04-01 至 2022-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027412&HistoricalAwards=false
• 关键词: RAPID; Using; location; based; big

The outbreak of COVID-19 in the U.S. provides an important opportunity for researchers to study the impacts of a rapidly expanding pandemic on human mobility. This research investigates how to measure changes in collective movement of people in response to the fast-evolving COVID-19 outbreak using large datasets of passively collected location data. It examines how locations within a state respond to public policy implementation and times of critical public messaging. Detailed knowledge on movement patterns of people can help public officials identify hotspots and critically isolated populations, as well as shed light on those groups who continue to travel for work or other purposes. This research contributes to improving the public response to an emergency and contributes to bridging different stakeholder mitigation strategies.Detailed knowledge of how people respond to a fast-spreading global pandemic is very limited and our understanding of these responses is mostly for small areas. This research will use a near real-time location-based dataset passively collected through the use of location-based apps during the period of pandemic. The project will develop scalable, big location-based algorithms to extract trips and examine the evolution of mobility patterns throughout the pandemic, and identify different mobility patterns. We will develop map-reduce based distributed algorithms to scale up mobility measure calculations based on the big location-based data as well as develop entropy measures to capture the time-varying characteristics associated with the travel patterns, and design strategies to correct biases that may be present in the location data. The methods and results of this research will be useful for understanding mobility during other hazards that affect communities, such as severe flooding to understand how travel is changed as a result of imperatives stemming from both the hazard and policy directives.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.

COVID-19 在美国的爆发为研究人员提供了一个重要的机会，以研究迅速蔓延的流行病对人类流动的影响。本研究探讨如何使用被动收集的位置数据的大型数据集来衡量人们集体流动的变化，以应对快速发展的 COVID-19 疫情。它研究了州内的各个地点如何响应公共政策的实施和关键公共信息传递的时间。关于人员流动模式的详细了解可以帮助公职人员识别热点地区和严重孤立的人群，并了解那些继续因工作或其他目的出行的群体。这项研究有助于改善公众对紧急情况的反应，并有助于弥合不同利益相关者的缓解策略。人们如何应对快速蔓延的全球流行病的详细知识非常有限，而且我们对这些反应的了解主要针对小范围。这项研究将使用在大流行期间通过使用基于位置的应用程序被动收集的近乎实时的基于位置的数据集。该项目将开发可扩展的、基于位置的大型算法来提取行程并检查整个大流行期间流动模式的演变，并识别不同的流动模式。我们将开发基于地图缩减的分布式算法，以扩大基于大位置数据的移动性度量计算，并开发熵度量来捕获与出行模式相关的时变特征，并设计策略来纠正位置数据中可能存在的偏差。这项研究的方法和结果将有助于了解影响社区的其他灾害（例如严重洪水）期间的流动性，以了解灾害和政策指令的要求如何改变出行。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

Understanding the Drivers of Mobility during the COVID-19 Pandemic in Florida, USA Using a Machine Learning Approach

• DOI: 10.3390/ijgi10070440
• 发表时间: 2021-06
• 期刊: ISPRS Int. J. Geo Inf.
• 作者: Guiming Zhu;K. Stewart;D. Niemeier;Junchuan Fan