A two-group epidemiological model: Stability analysis and numerical simulation using neural networks

Abstract

This work has two principal goals. First, we investigate the asymptotic behavior of a two-group epidemiological model and determine the expression of its basic reproduction number using the dynamical systems approach based on the spectral radius of the relative matrix. Second, we simulate the obtained analytical results using a new deep learning method that associates the ordinary differential equations governing the model to neural networks. A general disease-free equilibrium is considered and sufficient conditions of stability and convergence are formulated. A detailed description of the neural network model used in the simulation is provided. Moreover, the proposed deep learning simulation algorithm is compared to the simulation provided by “odeint”, a function from “SciPy” which is a Python library of mathematical routines.