
NSF Org: |
CCF Division of Computing and Communication Foundations |
Recipient: |
|
Initial Amendment Date: | April 16, 2020 |
Latest Amendment Date: | April 16, 2020 |
Award Number: | 2029044 |
Award Instrument: | Standard Grant |
Program Manager: |
Phillip Regalia
pregalia@nsf.gov (703)292-2981 CCF Division of Computing and Communication Foundations CSE Directorate for Computer and Information Science and Engineering |
Start Date: | May 1, 2020 |
End Date: | April 30, 2022 (Estimated) |
Total Intended Award Amount: | $199,449.00 |
Total Awarded Amount to Date: | $199,449.00 |
Funds Obligated to Date: |
|
History of Investigator: |
|
Recipient Sponsored Research Office: |
660 S MILL AVENUE STE 204 TEMPE AZ US 85281-3670 (480)965-5479 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
P.O. Box 876011 Tempe AZ US 85287-6011 |
Primary Place of
Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): | COVID-19 Research |
Primary Program Source: |
|
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.070 |
ABSTRACT
Corona Virus Disease 2019 (COVID-19) has emerged as a public health crisis of global proportions. As of April 10, 2020, there are approximately 1.7 million confirmed COVID-19 cases in more than 180 countries, with over 100,000 deaths. In the US, there are more than 500,000 confirmed cases and nearly 20,000 fatalities, and these numbers are continuing to rise sharply. There is a clear and acute need for ensuring the availability of infrastructure and critical services as the epidemic progresses. Current plans for controlling the epidemic are based on forecasts from well established ?compartment? models for epidemic prediction. These models rely on differential equations based on assumptions of homogeneous populations, homogeneous mixing, and knowledge of several critical hyperparameters such as the base reproduction rate. It is well known among experts in infectious diseases and epidemic management that fitting observed data to the parameters of such models is an exercise in characterizing the epidemiology as opposed to generating valid and actionable predictions. Consequently, there is an urgent need to significantly update these models to account for the data collected on the ground from multiple data sources and locations. This is especially relevant in engineering preemptive interventions to check disease spread. Current COVID disease data are organized in a geospatial format, i.e., infected, deceased, and suspected cases indexed by geolocation, which can range from city-, county-, or state-level coarseness. This project aims to develop and demonstrate techniques that use the geospatial nature of the data, the temporal evolution of disease statistics (along with predictions), and synthesis of multiple sources of data to help rapidly and preemptively allocate available medical resources toward the areas of greatest need.
Modeling the COVID-19 epidemic and designing interventions are significant challenges. This project looks at the problem through the lens of graph analytics. In particular, it seeks to use similarity information between geospatial regions of interest to improve epidemic predictions and to design effective interventions. As a first step, the problem of epidemic prediction is being modeled as the reconstruction of a high-dimensional dynamical system from low-dimensional observations. The estimates of a model thus learned will be enhanced by leveraging similarity information between the localities of interest. While the geospatial proximity graph is a natural candidate for the graph of similarities, it fails to capture long-range statistical dependencies between geographical regions based on other factors such as the sociological and biological features of a population. Using techniques from graphical modeling, this project will develop new techniques for learning statistically meaningful graphs for epidemic modeling during an ongoing pandemic. Furthermore, the accurate time-series prediction generated will be combined with the graph-based similarity measures to design effective interventions to check the spread of the epidemic. This is being approached using a stochastic formulation and emerging methods for anomaly detection on graphs with time series observations; optimal policies based on these paradigms will be translated into interventional strategies for an evolving pandemic. The project leverages partnerships with local community stakeholders in Maricopa County and the State of Arizona through the Knowledge Exchange for Resilience (KER) to implement the methodologies developed, and to ensure its technical advances can produce meaningful insights that can generalize nationally and globally.
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.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Overview of the Project. This RAPID project was proposed at the peak of the first-wave of the Corona Virus Disease 2019 (COVID-19) which emerged as a pandemic and public health crisis of global proportions. This highlighted a clear need for ensuring the availability of infrastructure and critical service, not just for this pandemic, but future ones as well. Current plans for understanding and controlling the epidemic are based on forecasts from well established ?compartment? models for epidemic prediction. These models rely on differential equations based on assumptions of homogeneous populations, homogeneous mixing, and knowledge of several critical hyperparameters such as the base reproduction rate (the so-called R0). It is well known among experts in infectious diseases and epidemic management that fitting observed data to the parameters of such models is an exercise in characterizing the epidemiology as opposed to generating valid and actionable predictions. There is therefore an urgent need to significantly update these models to account for the data collected on the ground from multiple data sources and locations. This is particularly relevant if one needs to engineer preemptive interventions to check disease spread. Current COVID disease data are organized in a geo-spatial format, i.e., infected, deceased, and suspected cases indexed by geolocation, which can range from city-, county-, or state-level coarseness. This aims of this project is to develop and demonstrate techniques that use the geospatial nature of the data, the temporal evolution of disease statistics (along with predictions thereof), and the synthesis of multiple sources of data to help in rapidly and preemptively allocating available medical resources toward the areas of greatest need.
The main outcomes of the project include:
- Understanding the patchwork pandemic. The first major outcome of the project is an empirical study of the uneven outcomes of the COVID-19 pandemic across the United States. The underlying complex pattern of drivers and its impact on public health outcomes state by state revealed by this line of work has raised questions about the utility of any national scale approach to understanding the pandemic. This line of work looks to expand upon public health literature especially with the view of helping incorporate fundamental geographic concepts to creatively develop modeling and interpretations that offer value for both informing and holding accountable local decision makers.
- Inference, Control, and Learning in Networked Systems. The COVID-19 pandemic highlighted the need for concerted modeling and intervention strategies across various geospatial locations. A major outcome of this RAPID project was the design, development, and analysis of a host of techniques that allow one to perform inference (say for modeling and prediction) and intervention (or control) when one has a cohort of time-evolving phenomena that are spatially linked. This work was supplemented by novel techniques for robustly learning the topology of such networked systems.
Aside from the technical contributions to various fields such as geography, statistics, machine learning, and computer science, the project also enabled the training of the next generation of scientists, engineers, and geographers ranging from high-school students to Ph.D students. The team also made an impact on the broader community by building (and continuing to maintain) a COVID-19 metadata repository, a disnformation detection systemn called TellMe, and a bilingual fake news dataset MM-COVID. Further, the participants in the project engaged with local data providers (in Arizona) to create sets of dashboards around specific areas of interest to community partners that intersect with pandemic realities. This included the activation of YouthMappers, a global youth crowdsourced mapping campaign, to add clinics to publicly available open world maps.
Last Modified: 08/31/2022
Modified by: Gautam Dasarathy
Please report errors in award information by writing to: awardsearch@nsf.gov.