RAPID: COVID-19-Net: Integrating Health, Pathogen and Environmental Data into a Knowledge Graph for Case Tracking, Analysis, and Forecasting

点击翻译按钮获取中文摘要

This COVID-19 RAPID research program could help answer several key questions about the pandemic, such as “What characteristics are in common among outbreaks in the US and other locations?”, “How different are viral strains, and how these differences affect transmission in different regions?”, or “How similar or different the patterns of the coronavirus infection spread and its impacts are compared to previous pandemics?” The multitude of diverse COVID-19-related data streams, which are rapidly made available online with little coordination or reliance on common standards, creates enormous challenges for researchers trying to answer such questions today, and analyze and predict patterns of the pandemic in its cross-disciplinary complexity. This project will do so by linking diverse information about pathogens, health data, and environmental indicators into a common knowledge graph, to let researchers trace the virus in different geographic conditions and provide input into effective intervention policies. The core technical component of the project is a COVID-19 knowledge graph, which represents linked facts about different aspects of the pandemic, from scientific literature and large data collections and models. The project will develop a novel methodology for creating a knowledge graph from disparate sources describing pathogens, population health, environmental conditions, and critical infrastructure components. The graph will be created in coordination with several partner projects working on the NSF Open Knowledge Network. This will ensure that additional knowledge domains can be integrated to support cross-disciplinary analysis. The results of the collaborative knowledge network development will be published as a continuously updated online dashboard for the general public and a collection of Jupyter Notebooks, open source software to enable interactive computing, to help researchers explore various aspects of the knowledge graph and improve our understanding of how the virus is spread and what intervention strategies are potentially most effective.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.