Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kisselev, Petr, Seshaiyer, Padmanabhan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.02043
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910772207026176
author Kisselev, Petr
Seshaiyer, Padmanabhan
author_facet Kisselev, Petr
Seshaiyer, Padmanabhan
contents Graph convolutional neural networks (GCNs) have shown tremendous promise in addressing data-intensive challenges in recent years. In particular, some attempts have been made to improve predictions of Susceptible-Infected-Recovered (SIR) models by incorporating human mobility between metapopulations and using graph approaches to estimate corresponding hyperparameters. Recently, researchers have found that a hybrid GCN-SIR approach outperformed existing methodologies when used on the data collected on a precinct level in Japan. In our work, we extend this approach to data collected from the continental US, adjusting for the differing mobility patterns and varying policy responses. We also develop the strategy for real-time continuous estimation of the reproduction number and study the accuracy of model predictions for the overall population as well as individual states. Strengths and limitations of the GCN-SIR approach are discussed as a potential candidate for modeling disease dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling COVID-19 spread in the USA using metapopulation SIR models coupled with graph convolutional neural networks
Kisselev, Petr
Seshaiyer, Padmanabhan
Machine Learning
Dynamical Systems
Populations and Evolution
92-10 (Primary) 68T07 (Secondary)
Graph convolutional neural networks (GCNs) have shown tremendous promise in addressing data-intensive challenges in recent years. In particular, some attempts have been made to improve predictions of Susceptible-Infected-Recovered (SIR) models by incorporating human mobility between metapopulations and using graph approaches to estimate corresponding hyperparameters. Recently, researchers have found that a hybrid GCN-SIR approach outperformed existing methodologies when used on the data collected on a precinct level in Japan. In our work, we extend this approach to data collected from the continental US, adjusting for the differing mobility patterns and varying policy responses. We also develop the strategy for real-time continuous estimation of the reproduction number and study the accuracy of model predictions for the overall population as well as individual states. Strengths and limitations of the GCN-SIR approach are discussed as a potential candidate for modeling disease dynamics.
title Modeling COVID-19 spread in the USA using metapopulation SIR models coupled with graph convolutional neural networks
topic Machine Learning
Dynamical Systems
Populations and Evolution
92-10 (Primary) 68T07 (Secondary)
url https://arxiv.org/abs/2501.02043