Optimisation of non-pharmaceutical measures in COVID-19 growth via neural networks.

This study seeks to quantify the impact of government actions in mitigating viral transmission of SARS-CoV-2. On 19 March, the World Health Organisation declared a pandemic. Through this global spread, many nations have witnessed exponential growth of confirmed cases brought under control by severe mass quarantine or lockdown measures. However, some nations have, through a different timeline of actions, prevented this exponential growth. Currently whilst some continue to tackle exponential growth, others attempt to safely lift restrictions whilst avoiding a resurgence. To quantify the impact of government actions and support existing theories as well as policy makers, a data-driven model is developed. Data for two nations, Italy and Taiwan, is gathered and used to train several neural networks. The results of the best-performing model, the Long Short Term Neural Network, are optimized to investigate a different scenario of mitigation measures for both nations. It is found a larger and earlier testing campaign with tighter border control benefit both nations by resulting in significantly less confirmed cases. Interestingly, this scenario couples with an earlier but milder implementation of nationwide restrictions for Italy, thus supporting Taiwan's lack of a nationwide lockdown