Data-driven optimal control of a SEIR model for COVID-19

TL;DR

This paper introduces a data-driven optimal control method for COVID-19's SEIR epidemic model, using real data to dynamically learn parameters, forecast outbreak evolution, and optimize intervention strategies.

Contribution

It develops a novel approach integrating partial data with epidemic dynamics, employing time-varying parameters and efficient algorithms based on Pontryagin's Maximum Principle.

Findings

Effective forecasting of COVID-19 outbreak evolution.

Demonstrated the model's ability to optimize control measures.

Validated the approach with numerical experiments.

Abstract

We present a data-driven optimal control approach which integrates the reported partial data with the epidemic dynamics for COVID-19. We use a basic Susceptible-Exposed-Infectious-Recovered (SEIR) model, the model parameters are time-varying and learned from the data. This approach serves to forecast the evolution of the outbreak over a relatively short time period and provide scheduled controls of the epidemic. We provide efficient numerical algorithms based on a generalized Pontryagin Maximum Principle associated with the optimal control theory. Numerical experiments demonstrate the effective performance of the proposed model and its numerical approximations.