Time-varying compartmental models with neural networks for pandemic infection forecasting

The emergence and spread of deadly pandemics has repeatedly occurred throughout history, causing widespread infections and life loss. Forecasting the progression of pandemics is crucial for decision-makers to achieve its mitigation. This predictive task constitutes a challenge due to the non-stationary nature of pandemics, and changes in adopted policies and social reactions to them. Motivated by this, we present a hybrid pandemic infection forecasting methodology that integrates compartmental modelling and machine learning approaches. In particular, we develop a compartmental model that includes time-varying infection rates, which are the key parameters that determine a pandemic's evolution. To identify the time-dependent infection rates, we establish a hybrid methodology that combines the developed compartmental model and tools from optimization and neural networks. Specifically, the proposed methodology estimates the infection rates by fitting the model to the available data, regarding the COVID-19 pandemic in Cyprus, and then predicting their future values through either a) extrapolation, or b) using neural networks. The developed approach exhibits strong accuracy in predicting infections seven days in advance, achieving low average percentage errors both using the extrapolation (9.90%) and neural network (5.04%) approaches.