A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases
A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases
Modeling the spread of infectious diseases in space and time needs to take care of complex dependencies and uncertainties. Machine learning methods, and neural networks, in particular, are useful in modeling this sort of complex problems, although they generally lack of probabilistic interpretations. We propose a neural network method embedded in a Bayesian framework for modeling and predicting the number of cases of infectious diseases in areal units. A key feature is that our combined model considers the impact of human movement on the spread of the infectious disease, as an additional random factor to the also considered spatial neighborhood and temporal correlation components. Our model is evaluated over a COVID-19 dataset for 245 health zones of Castilla-Leon (Spain). The results show that a Bayesian model informed by a neural network method is generally able to predict the number of cases of COVID-19 in both space and time, with the human mobility factor having a strong influence on the model, together with the number of infections and deaths in nearby areas.
2265-2283
Niraula, Poshan
33532a2f-f6a7-479e-8131-40609ff1ccb3
Mateu, Jorge
522f2e31-3f2f-4a7e-b671-94255ae74e48
Chaudhuri, Somnath
ae0507e0-f920-4438-bc9f-ecdd5ac8967a
25 January 2022
Niraula, Poshan
33532a2f-f6a7-479e-8131-40609ff1ccb3
Mateu, Jorge
522f2e31-3f2f-4a7e-b671-94255ae74e48
Chaudhuri, Somnath
ae0507e0-f920-4438-bc9f-ecdd5ac8967a
Niraula, Poshan, Mateu, Jorge and Chaudhuri, Somnath
(2022)
A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases.
Stochastic Environmental Research and Risk Assessment, 36, .
(doi:10.1007/s00477-021-02168-w).
Abstract
Modeling the spread of infectious diseases in space and time needs to take care of complex dependencies and uncertainties. Machine learning methods, and neural networks, in particular, are useful in modeling this sort of complex problems, although they generally lack of probabilistic interpretations. We propose a neural network method embedded in a Bayesian framework for modeling and predicting the number of cases of infectious diseases in areal units. A key feature is that our combined model considers the impact of human movement on the spread of the infectious disease, as an additional random factor to the also considered spatial neighborhood and temporal correlation components. Our model is evaluated over a COVID-19 dataset for 245 health zones of Castilla-Leon (Spain). The results show that a Bayesian model informed by a neural network method is generally able to predict the number of cases of COVID-19 in both space and time, with the human mobility factor having a strong influence on the model, together with the number of infections and deaths in nearby areas.
Text
SERRA_Accepted_Manuscript
More information
Accepted/In Press date: 30 December 2021
Published date: 25 January 2022
Identifiers
Local EPrints ID: 502596
URI: http://eprints.soton.ac.uk/id/eprint/502596
ISSN: 1436-3240
PURE UUID: e2653f3b-2f4b-4eaf-8a47-a79822d94a64
Catalogue record
Date deposited: 02 Jul 2025 10:04
Last modified: 05 Jul 2025 02:18
Export record
Altmetrics
Contributors
Author:
Poshan Niraula
Author:
Jorge Mateu
Author:
Somnath Chaudhuri
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics