PIPP Phase I: Heterogeneous Model Integration for Infectious Disease Intelligence

点击翻译按钮获取中文摘要

During outbreaks of emerging infectious diseases, leaders in government and the private sector must make timely decisions to control spread and mitigate damages. Computer models are often used to support decision-making, for instance to provide forecasts of future transmission or to understand how public policies may be received by the population. However, infectious disease intelligence suffers from the fact that infectious disease modeling is largely disjointed because most models examine only one or two aspects of transmission, whereas epidemics and pandemics are complicated, multi-faceted events that touch on many aspects of society. For this reason, intelligence for pandemic prediction and prevention must be a multidisciplinary endeavor that integrates diverse theories, concepts, and frameworks from the natural and social sciences, although a framework for this integration is currently lacking. To fill this gap, this project will develop a Systems-of-Systems (SoS) framework that allows the knowledge gained from different disciplinary approaches to be integrated with one another. Anticipated outcomes of this framework include improved situation awareness, real-time forecasting, risk analysis, public policy interventions, and individual decision-making.The SoS modeling approach will address the grand challenge of modeling interdependence across scales by allowing for interactive feedback through the integration of information from different sources. This project will plan and execute six Demonstration Projects (DPs) that individually connect at least two different scales and/or scientific methodologies. All DPs will focus on Highly Pathogenic Avian Influenza (HPAI) as a model for the spillover and emergence of an emerging respiratory pathogen of animal origin. DP1 will develop an automated reasoning engine -- a kind of Artificial Intelligence (AI) that learns and reasons from a comprehensive, multi-disciplinary representational ontology of knowledge about HPAI across disciplines. DP2 will develop prototype explainable AI algorithms to generalize our understanding of how vaccines can be used to contain pandemics. DP3 will collect new data on the behavioral responsiveness of the population to health communications and integrate that data into disease transmission models. DP4 will develop a new dynamical model to characterize how variation in compliance with public policies creates epidemic tipping points and how these tipping points can be anticipated. DP5 will develop new methods for estimating the pandemic potential of wildlife pathogens from genetic data. DP6 will develop techniques for extrapolating the results of laboratory experiments to characterize the pandemic potential of virus lineages before they emerge in the human population.This award is supported by the cross-directorate Predictive Intelligence for Pandemic Prevention Phase I (PIPP) program, which is jointly funded by the Directorates for Biological Sciences (BIO), Computer Information Science and Engineering (CISE), Social, Behavioral and Economic Sciences (SBE) and Engineering (ENG).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.