Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread

Abstract

Studying the dynamics of COVID-19 is of paramount importance to understanding the efficiency of restrictive measures and develop strategies to defend against upcoming contagion waves. In this work, we study the spread of COVID-19 using a semi-supervised neural network and assuming a passive part of the population remains isolated from the virus dynamics. We start with an unsupervised neural network that learns solutions of differential equations for different modeling parameters and initial conditions. A supervised method then solves the inverse problem by estimating the optimal conditions that generate functions to fit the data for those infected by, recovered from, and deceased due to COVID-19. This semi-supervised approach incorporates real data to determine the evolution of the spread, the passive population, and the basic reproduction number for different countries.

arXiv comment5 pages, 3 figures

References in corpus (8)

• A SIDARTHE Model of COVID-19 Epidemic in Italy
• Inferring change points in the COVID-19 spreading reveals the effectiveness of interventions
• Mathematical Modeling of COVID-19 Transmission Dynamics with a Case Study of Wuhan
• Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: A data-driven analysis
• Estimating the infection horizon of COVID-19 in eight countries with a data-driven approach
• The first 100 days: modeling the evolution of the COVID-19 pandemic
• Neural Networks Trained to Solve Differential Equations Learn General Representations
• Solving Differential Equations Using Neural Network Solution Bundles

Cited by in corpus (4)

• Modeling the effect of the vaccination campaign on the Covid-19 pandemic
• Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
• Semi-supervised Learning for COVID-19 Image Classification via ResNet
• A New Artificial Neuron Proposal with Trainable Simultaneous Local and Global Activation Function