Calibrating deterministic compartmental models of infection dynamics using neural network and data sampling approaches

Pandemics caused by the new coronavirus has spread globally with a strong contagion rate and death rate. In this paper the deterministic SEIR model is calibrated with Metropolis Hasting algorithm, physics-informed neural network (PINN) and latin hypercube sampling (LHS) method to identify the optimal hyper parameters of SEIR model and to forecast the dynamics of COVID-19 incidence in Saint-Petersburg, Russia, its retrospective analysis and evaluation of the effectiveness of control measures.