Impact studies of nationwide measures COVID-19 anti-pandemic: compartmental model and machine learning

TL;DR

This paper analyzes the impact of nationwide COVID-19 measures using a compartmental model and machine learning, comparing deterministic and ML-based forecasts to understand pandemic evolution under different policy scenarios.

Contribution

It introduces a combined approach of compartmental modeling and machine learning to evaluate and forecast COVID-19 pandemic dynamics considering nationwide measures.

Findings

Different pandemic evolution scenarios based on measure levels.

Machine learning tools provide comparable or improved forecasts.

Deterministic and ML models show varying sensitivities to measures.

Abstract

In this paper, we deal with the study of the impact of nationwide measures COVID-19 anti-pandemic. We drive two processes to analyze COVID-19 data considering measures. We associate level of nationwide measure with value of parameters related to the contact rate of the model. Then a parametric solve, with respect to those parameters of measures, shows different possibilities of the evolution of the pandemic. Two machine learning tools are used to forecast the evolution of the pandemic. Finally, we show comparison between deterministic and two machine learning tools.