Digital twins based on bidirectional LSTM and GAN for modelling the COVID-19 pandemic

TL;DR

This paper introduces digital twins using bidirectional LSTM and GAN to model COVID-19 spread, demonstrating accurate predictions and potential for application to various towns and more complex epidemiological models.

Contribution

It presents novel digital twin frameworks based on bidirectional LSTM and GAN for epidemiological modeling of COVID-19, incorporating spatial variation and data correction.

Findings

Both models accurately predict SEIRS data.

Models are data-agnostic and adaptable to different towns.

Frameworks can incorporate additional compartments for realism.

Abstract

The outbreak of the coronavirus disease 2019 (COVID-19) has now spread throughout the globe infecting over 150 million people and causing the death of over 3.2 million people. Thus, there is an urgent need to study the dynamics of epidemiological models to gain a better understanding of how such diseases spread. While epidemiological models can be computationally expensive, recent advances in machine learning techniques have given rise to neural networks with the ability to learn and predict complex dynamics at reduced computational costs. Here we introduce two digital twins of a SEIRS model applied to an idealised town. The SEIRS model has been modified to take account of spatial variation and, where possible, the model parameters are based on official virus spreading data from the UK. We compare predictions from a data-corrected Bidirectional Long Short-Term Memory network and a predictive Generative Adversarial Network. The predictions given by these two frameworks are accurate when compared to the original SEIRS model data. Additionally, these frameworks are data-agnostic and could be applied to towns, idealised or real, in the UK or in other countries. Also, more compartments could be included in the SEIRS model, in order to study more realistic epidemiological behaviour.