Modeling Omicron Dynamics and Development in China: with a Deep Learning Enhanced Compartmental Model

Abstract

Abstract Background: The mainstream compartmental models require stochastic parameterization to estimate the transmission parameters between compartments, which depends upon detailed statistics on epidemiological transmission characteristics that are economically and resource-wide expensive to collect. As an alternative, deep learning techniques are effective in estimating these stochastic parameters with greatly reduced dependency on data particularity. Objectives: We apply deep learning techniques as a lower data dependency alternative to estimate transmission parameters of a customized compartmental model, for the purpose of simulating the dynamics of the Omicron phase of the COVID-19 epidemics and projecting its further development in China. Methods: We apply deep learning to estimate the transmission parameters of a customized compartmental model and then feed the estimated transmission parameters to the compartmental model to predict the development of Omicron epidemics in China for 28 days. Results: In mainland China, the daily Omicron infection increase is between 60 and 260 in the 28-day forecast period between June 4 and July 1, 2022. On July 1, 2022, there would be 768,622 cumulative confirmed cases and 591 cumulative deceased cases. The average levels of prediction accuracy of the model are 98% and 92% for the number of infections and deaths, respectively. Conclusions: The effectiveness of prevalent compartmental modes depends upon detailed statistics on epidemiological transmission characteristics. As an alternative, deep learning techniques are effective in estimating these stochastic parameters with greatly reduced dependency on data particularity. Our model demonstrates the efficacy and potential of applying deep learning methodologies in predicting the dynamics of infectious diseases.