Machine learning spatio-temporal epidemiological model to evaluate Germany-county-level COVID-19 risk

TL;DR

This paper introduces a machine learning-based spatiotemporal epidemiological model combining cellular automaton and SUIR dynamics to predict COVID-19 risks at the county level in Germany, aiding policy decisions.

Contribution

It presents a novel CA-SUIR model integrating spatial and temporal data for multi-level COVID-19 risk prediction, improving policy evaluation accuracy.

Findings

Accurately projected COVID-19 prevalence in 412 German counties.

Predicted fatalities could be reduced from 34.5k to below 21k with effective policies.

Demonstrated the model's utility in assessing travel restrictions and intervention strategies.

Abstract

As the COVID-19 pandemic continues to ravage the world, it is of critical significance to provide a timely risk prediction of the COVID-19 in multi-level. To implement it and evaluate the public health policies, we develop a framework with machine learning assisted to extract epidemic dynamics from the infection data, in which contains a county-level spatiotemporal epidemiological model that combines a spatial Cellular Automaton (CA) with a temporal Susceptible-Undiagnosed-Infected-Removed (SUIR) model. Compared with the existing time risk prediction models, the proposed CA-SUIR model shows the multi-level risk of the county to the government and coronavirus transmission patterns under different policies. This new toolbox is first utilized to the projection of the multi-level COVID-19 prevalence over 412 Landkreis (counties) in Germany, including t-day-ahead risk forecast and the risk assessment to the travel restriction policy. As a practical illustration, we predict the situation at Christmas where the worst fatalities are 34.5 thousand, effective policies could contain it to below 21 thousand. Such intervenable evaluation system could help decide on economic restarting and public health policies making in pandemic.