Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks

TL;DR

This paper introduces a novel COVID-19 forecasting method using spatio-temporal graph neural networks that leverage mobility data to improve prediction accuracy at the county level.

Contribution

It presents a new GNN-based approach that models human mobility and spatial-temporal dynamics for infectious disease forecasting.

Findings

6% reduction in RMSLE compared to baselines

Pearson Correlation improved from 0.9978 to 0.998

Effective modeling of complex COVID-19 spread dynamics

Abstract

In this work, we examine a novel forecasting approach for COVID-19 case prediction that uses Graph Neural Networks and mobility data. In contrast to existing time series forecasting models, the proposed approach learns from a single large-scale spatio-temporal graph, where nodes represent the region-level human mobility, spatial edges represent the human mobility based inter-region connectivity, and temporal edges represent node features through time. We evaluate this approach on the US county level COVID-19 dataset, and demonstrate that the rich spatial and temporal information leveraged by the graph neural network allows the model to learn complex dynamics. We show a 6% reduction of RMSLE and an absolute Pearson Correlation improvement from 0.9978 to 0.998 compared to the best performing baseline models. This novel source of information combined with graph based deep learning approaches can be a powerful tool to understand the spread and evolution of COVID-19. We encourage others to further develop a novel modeling paradigm for infectious disease based on GNNs and high resolution mobility data.