Modeling COVID-19 spread in the USA using metapopulation SIR models coupled with graph convolutional neural networks

TL;DR

This paper extends a hybrid graph convolutional neural network and SIR model to predict COVID-19 spread across the US, incorporating mobility patterns and policy responses for real-time estimation and accuracy assessment.

Contribution

It adapts and applies a GCN-SIR hybrid model to US data, enabling real-time estimation of disease spread and analyzing its strengths and limitations.

Findings

Effective real-time estimation of the reproduction number.

Model accurately predicts disease dynamics at state and national levels.

Identifies limitations in modeling heterogeneous mobility patterns.

Abstract

Graph convolutional neural networks (GCNs) have shown tremendous promise in addressing data-intensive challenges in recent years. In particular, some attempts have been made to improve predictions of Susceptible-Infected-Recovered (SIR) models by incorporating human mobility between metapopulations and using graph approaches to estimate corresponding hyperparameters. Recently, researchers have found that a hybrid GCN-SIR approach outperformed existing methodologies when used on the data collected on a precinct level in Japan. In our work, we extend this approach to data collected from the continental US, adjusting for the differing mobility patterns and varying policy responses. We also develop the strategy for real-time continuous estimation of the reproduction number and study the accuracy of model predictions for the overall population as well as individual states. Strengths and limitations of the GCN-SIR approach are discussed as a potential candidate for modeling disease dynamics.