ESTIMATING TIME-VARYING REPRODUCTION NUMBER BY DEEP LEARNING TECHNIQUES

Estimating time-varying reproduction number R_t is important for quantifying the transmission ability, capturing the trend of infectious disease and assessing the effectiveness of public health intervention measures. However, accurate estimation of R_t remains a challenging work. Deep neural networks are uniform approximators and have an unreasonable and counterintuitive effectiveness in learning unknown functions, thus can be applied to represent R_t. In this paper, we will estimate R_t by universal differential equation method which embeds neural network R_t into a differential equation. Compared with other methods such as state space, EpiEstim and EpiNow2 methods, deep learning method can achieve better performance with fewer data sources.