Ensemble Forecasting of the Zika Space-Time Spread with Topological Data Analysis

• Activity Number: 319 - Innovative Approaches to the Study of an Epidemic
• Type: Contributed
• Date/Time: Wednesday, August 5, 2020 : 10:00 AM to 2:00 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Marwah Soliman* and Vyacheslav Lyubchich and Yulia Gel
• Companies: University of Texas At Dallas and University of Maryland and University of Texas at Dallas
• Keywords: Zika virus; Bayesian model averaging; machine learning; neural network; epidemics

Abstract

The records of the World Health Organization, the first formally reported incidence of Zika virus occurred in Brazil in May 2015. The abundance of mosquitoes and, as a result, the prevalence of Zika virus infections are common in areas which have high precipitation, high temperature, and high population density. Nonlinear spatio-temporal dependency of such data and lack of historical public health records make prediction of the virus spread particularly challenging. In this paper we enhance Zika forecasting by introducing the concepts of topological data analysis and, specifically, persistent homology of atmospheric variables, into the virus spread modeling. The key rationale is that topological summaries allow for capturing higher-order dependencies among atmospheric variables that otherwise might be unassessable via conventional spatio-temporal modelling approaches based on geographical proximity assessed via Euclidean distance. We introduce a new concept of cumulative Betti numbers and then integrate the cumulative Betti numbers as topological descriptors as topological descriptors into three predictive machine learning models: random forest, boosted reg and deep neural network