COVID-19 dynamics across the US: a deep learning study of human mobility and social behavior

DOI10.1016/j.cma.2021.113891zbMath1506.92084MaRDI QIDQ2237292

Paris Perdikaris, Hanwen Wang, Kevin Linka, Francisco Sahli Costabal, Mohamed Aziz Bhouri, Mathias Peirlinck, Ellen Kuhl

Publication date: 27 October 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2021.113891

zbMATH Keywords

sensitivity analysis; dynamical systems; neural networks; uncertainty quantification; scientific machine learning; epidemiology model discovery

Mathematics Subject Classification ID

92D30: Epidemiology

92D50: Animal behavior

Related Items

Identification of time delays in COVID-19 data, Modeling nonlocal behavior in epidemics via a reaction-diffusion system incorporating population movement along a network, Bayesian inference of heterogeneous epidemic models: application to COVID-19 spread accounting for long-term care facilities, Bayesian physics informed neural networks for real-world nonlinear dynamical systems, A new family of constitutive artificial neural networks towards automated model discovery

Uses Software

• Adam
• GitHub
• NUTS
• NumPyro

Cites Work

• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• NUTS
• NumPyro
• Visualizing the invisible: the effect of asymptomatic transmission on the outbreak dynamics of COVID-19
• Bayesian-based predictions of COVID-19 evolution in Texas using multispecies mixture-theoretic continuum models
• System inference for the spatio-temporal evolution of infectious diseases: Michigan in the time of COVID-19
• Dynamics identification and forecasting of COVID-19 by switching Kalman filters
• The Mathematics of Infectious Diseases
• Parameter estimation for stiff deterministic dynamical systems via ensemble Kalman filter
• A Bayesian filtering approach to layer stripping for electrical impedance tomography