RAPID: Monitoring the Spatial Spread of COVID-19 through the Lens of Human Movement using Big Social Media Data

人口流动是推动COVID-19空间传播的关键因素之一。在这种全球大流行期间，监测和分析人员流动模式或人口流动对于我们更好地了解人口层面当前和未来的感染风险至关重要。这项快速反应研究（Rapid）赠款将利用大社交媒体数据、人工智能（AI）和时空分析，通过人类流动模式在不同空间尺度（从地方到区域再到全球）监测和模拟COVID-19的空间传播。该项目的成果将通过互动式在线仪表板进行传播，提高政府官员和公众对形势的认识，提供见解，并促进公众对人在COVID-19危机演变过程中所起作用的集体认识。仪表板提供的信息可以帮助政府官员、公共卫生管理人员和应急响应人员回答大流行期间的关键问题，例如：“一个州、县或社区当前和未来的感染风险是什么？”“保持社交/身体距离的做法在遏制病毒方面的效果如何？”以及“重新开放我们的经济和社区的不同战略的后果是什么？”该项目的成功实施将有助于在新冠肺炎大流行和未来公共卫生危机期间促进国民健康、繁荣和福祉。该项目将通过吸引来自不同背景的研究生和本科生参与数据收集、分析、建模、工具开发以及社区外展和培训，支持教育和多样性。社交媒体大数据已广泛用于人类流动性研究，但在全球传染病传播背景下，很少有研究验证使用这些数据在不同地理尺度（例如，从地方到全球）研究人类运动的能力和局限性。通过利用该团队在空间计算、大数据分析、传染病建模、公共卫生教育和行为改变以及社区参与方面的专业知识，该项目旨在开发一种新的数据驱动方法，包括创新模型、高效计算算法和交互式仪表板，以监测、建模和绘制COVID-19的空间传播。具体而言，我们将(1)开发一种新的起源-目的地-时间数据模型，从数十亿个地理标记的社交媒体（Twitter）帖子中有效提取不同时空尺度的历史和近实时人口流动；(2)建立时空融合神经网络预测模型，结合人口流动和其他因素对未来感染潜力进行预测；(3)对不同空间尺度上的人口流动总量和每日确诊病例进行时空和地统计学分析，研究人员流动与病毒空间传播之间的时空动态和关联。本研究的方法学研究成果将对各种人类流动性研究的模型和方法学的发展、应用和扩展做出重大贡献。这项研究将促进地理空间科学的进步，并对公共卫生、自然灾害、交通和旅游等不同领域产生广泛影响，这些领域可以从更好地了解人类运动中受益。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。

Human population movement is among the critical dimension that drives the spatial spread of COVID-19. During such a global pandemic, monitoring and analyzing human movement patterns or population flows are critical for us to gain a better understanding into current and future infectious risk at the population level. This Rapid Response Research (RAPID) grant will utilize big social media data, artificial intelligence (AI), and spatiotemporal analysis to monitor and model the spatial spread of COVID-19 at different spatial scales (from local to regional to global) through the lens of human mobility patterns. Results of this project, disseminated through an interactive online dashboard, will provide enhanced situation awareness for government official and the public, offering insights and facilitating a collective public awareness of the role people play in the evolution of the COVID-19 crisis. The information provided by the dashboard can help government officials, public health managers and emergency responders to answer critical questions during the pandemic, such as: “What is the current and future infectious risk of a state, county, or community?”; “How effective are the social/physical distancing practice in containing the virus?”; and “What are the consequences for different strategies for reopening our economy and communities?”. The successful implementation of this project will advance the national health, prosperity, and welfare during COVID-19 pandemic and future public health crisis. This project will support education and diversity through engaging graduate and undergraduate students from different backgrounds in data collection, analysis, modeling, tool development, and community outreach and training.Big social media data have been widely used in human mobility studies, yet little research has been conducted to validate the capabilities and limitations of using these data for studying human movement at different geographic scales (e.g., from local to global) in the context of global infectious disease transmission. By leveraging the team’s expertise in spatial computing, big data analytics, infectious disease modeling, public health education and behavior modification, and community engagement, this project aims to develop a novel data-driven approach, including innovative models, efficient computing algorithms, and an interactive dashboard, to monitor, model and map the spatial spread of COVID-19. Specifically, we will (1) develop a novel origin-destination-time data model to efficiently extract historical and near real-time population flows at varying spatiotemporal scales from billions of geotagged social media (Twitter) posts; (2) develop a predictive model using a spatial-temporal fused neural network to estimate future infectious potential by incorporating population flows with other factors; and (3) perform spatiotemporal and geostatistical analysis for aggregated population flows and daily confirmed cases at varying spatial scales to examine the spatiotemporal dynamics and associations between human movement and spatial spread of the virus. Methodological findings of this project are expected to make significant contributions to the development, application, and extension of models and methodology in a variety of human mobility studies. This research will promote the progress of geospatial science and have broad impacts in diverse fields that can benefit from a better understanding of human movement, such as public health, natural hazard, transportation, and tourism.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.